[{"year":"2023","_id":"14105","date_created":"2023-08-21T12:11:38Z","oa_version":"Preprint","article_processing_charge":"No","quality_controlled":"1","abstract":[{"lang":"eng","text":"Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to inference. With no labels available this requires unsupervised objectives to adapt the model on the observed test data. In this paper, we propose Test-Time SelfTraining (TeST): a technique that takes as input a model trained on some source data and a novel data distribution at test time, and learns invariant and robust representations using a student-teacher framework. We find that models adapted using TeST significantly improve over baseline testtime adaptation algorithms. TeST achieves competitive performance to modern domain adaptation algorithms [4, 43], while having access to 5-10x less data at time of adaption. We thoroughly evaluate a variety of baselines on two tasks:\r\nobject detection and image segmentation and find that models adapted with TeST. We find that TeST sets the new stateof-the art for test-time domain adaptation algorithms. "}],"publication_status":"published","publication":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision","publication_identifier":{"eissn":["2642-9381"],"isbn":["9781665493475"]},"oa":1,"day":"06","citation":{"short":"S. Sinha, P. Gehler, F. Locatello, B. Schiele, in:, 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, Institute of Electrical and Electronics Engineers, 2023.","ieee":"S. Sinha, P. Gehler, F. Locatello, and B. Schiele, “TeST: Test-time Self-Training under distribution shift,” in <i>2023 IEEE/CVF Winter Conference on Applications of Computer Vision</i>, Waikoloa, HI, United States, 2023.","apa":"Sinha, S., Gehler, P., Locatello, F., &#38; Schiele, B. (2023). TeST: Test-time Self-Training under distribution shift. In <i>2023 IEEE/CVF Winter Conference on Applications of Computer Vision</i>. Waikoloa, HI, United States: Institute of Electrical and Electronics Engineers. <a href=\"https://doi.org/10.1109/wacv56688.2023.00278\">https://doi.org/10.1109/wacv56688.2023.00278</a>","ama":"Sinha S, Gehler P, Locatello F, Schiele B. TeST: Test-time Self-Training under distribution shift. In: <i>2023 IEEE/CVF Winter Conference on Applications of Computer Vision</i>. Institute of Electrical and Electronics Engineers; 2023. doi:<a href=\"https://doi.org/10.1109/wacv56688.2023.00278\">10.1109/wacv56688.2023.00278</a>","mla":"Sinha, Samarth, et al. “TeST: Test-Time Self-Training under Distribution Shift.” <i>2023 IEEE/CVF Winter Conference on Applications of Computer Vision</i>, Institute of Electrical and Electronics Engineers, 2023, doi:<a href=\"https://doi.org/10.1109/wacv56688.2023.00278\">10.1109/wacv56688.2023.00278</a>.","ista":"Sinha S, Gehler P, Locatello F, Schiele B. 2023. TeST: Test-time Self-Training under distribution shift. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. WACV: Winter Conference on Applications of Computer Vision.","chicago":"Sinha, Samarth, Peter Gehler, Francesco Locatello, and Bernt Schiele. “TeST: Test-Time Self-Training under Distribution Shift.” In <i>2023 IEEE/CVF Winter Conference on Applications of Computer Vision</i>. Institute of Electrical and Electronics Engineers, 2023. <a href=\"https://doi.org/10.1109/wacv56688.2023.00278\">https://doi.org/10.1109/wacv56688.2023.00278</a>."},"date_updated":"2023-09-06T10:26:56Z","author":[{"first_name":"Samarth","last_name":"Sinha","full_name":"Sinha, Samarth"},{"last_name":"Gehler","first_name":"Peter","full_name":"Gehler, Peter"},{"last_name":"Locatello","first_name":"Francesco","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4"},{"full_name":"Schiele, Bernt","first_name":"Bernt","last_name":"Schiele"}],"title":"TeST: Test-time Self-Training under distribution shift","external_id":{"arxiv":["2209.11459"]},"scopus_import":"1","conference":{"name":"WACV: Winter Conference on Applications of Computer Vision","location":"Waikoloa, HI, United States","start_date":"2023-01-02","end_date":"2023-01-07"},"arxiv":1,"main_file_link":[{"url":"https://arxiv.org/abs/2209.11459","open_access":"1"}],"department":[{"_id":"FrLo"}],"publisher":"Institute of Electrical and Electronics Engineers","month":"02","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"conference","extern":"1","language":[{"iso":"eng"}],"status":"public","doi":"10.1109/wacv56688.2023.00278","date_published":"2023-02-06T00:00:00Z"},{"volume":26,"type":"journal_article","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","file_date_updated":"2023-08-23T10:59:15Z","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"status":"public","language":[{"iso":"eng"}],"date_published":"2023-07-26T00:00:00Z","doi":"10.1007/s11040-023-09460-x","ddc":["510"],"intvolume":"        26","arxiv":1,"scopus_import":"1","acknowledgement":"D.M. and K.M. thank Robert Seiringer for helpful discussions. Open access funding provided by Institute of Science and Technology (IST Austria). Financial support from the Agence Nationale de la Recherche (ANR) through the projects ANR-17-CE40-0016, ANR-17-CE40-0007-01, ANR-17-EURE-0002 (J.L.) and from the European Union’s Horizon 2020 research and innovation programme under the Maria Skłodowska-Curie grant agreement No. 665386 (K.M.) is gratefully acknowledged.","month":"07","department":[{"_id":"RoSe"}],"publisher":"Springer Nature","isi":1,"author":[{"full_name":"Lampart, Jonas","first_name":"Jonas","last_name":"Lampart"},{"full_name":"Mitrouskas, David Johannes","id":"cbddacee-2b11-11eb-a02e-a2e14d04e52d","last_name":"Mitrouskas","first_name":"David Johannes"},{"id":"316457FC-F248-11E8-B48F-1D18A9856A87","full_name":"Mysliwy, Krzysztof","first_name":"Krzysztof","last_name":"Mysliwy"}],"citation":{"chicago":"Lampart, Jonas, David Johannes Mitrouskas, and Krzysztof Mysliwy. “On the Global Minimum of the Energy–Momentum Relation for the Polaron.” <i>Mathematical Physics, Analysis and Geometry</i>. Springer Nature, 2023. <a href=\"https://doi.org/10.1007/s11040-023-09460-x\">https://doi.org/10.1007/s11040-023-09460-x</a>.","ista":"Lampart J, Mitrouskas DJ, Mysliwy K. 2023. On the global minimum of the energy–momentum relation for the polaron. Mathematical Physics, Analysis and Geometry. 26(3), 17.","mla":"Lampart, Jonas, et al. “On the Global Minimum of the Energy–Momentum Relation for the Polaron.” <i>Mathematical Physics, Analysis and Geometry</i>, vol. 26, no. 3, 17, Springer Nature, 2023, doi:<a href=\"https://doi.org/10.1007/s11040-023-09460-x\">10.1007/s11040-023-09460-x</a>.","apa":"Lampart, J., Mitrouskas, D. J., &#38; Mysliwy, K. (2023). On the global minimum of the energy–momentum relation for the polaron. <i>Mathematical Physics, Analysis and Geometry</i>. Springer Nature. <a href=\"https://doi.org/10.1007/s11040-023-09460-x\">https://doi.org/10.1007/s11040-023-09460-x</a>","ieee":"J. Lampart, D. J. Mitrouskas, and K. Mysliwy, “On the global minimum of the energy–momentum relation for the polaron,” <i>Mathematical Physics, Analysis and Geometry</i>, vol. 26, no. 3. Springer Nature, 2023.","ama":"Lampart J, Mitrouskas DJ, Mysliwy K. On the global minimum of the energy–momentum relation for the polaron. <i>Mathematical Physics, Analysis and Geometry</i>. 2023;26(3). doi:<a href=\"https://doi.org/10.1007/s11040-023-09460-x\">10.1007/s11040-023-09460-x</a>","short":"J. Lampart, D.J. Mitrouskas, K. Mysliwy, Mathematical Physics, Analysis and Geometry 26 (2023)."},"date_updated":"2023-12-13T12:16:19Z","oa":1,"publication":"Mathematical Physics, Analysis and Geometry","publication_identifier":{"issn":["1385-0172"],"eissn":["1572-9656"]},"day":"26","external_id":{"arxiv":["2206.14708"],"isi":["001032992600001"]},"title":"On the global minimum of the energy–momentum relation for the polaron","article_number":"17","issue":"3","has_accepted_license":"1","_id":"14192","year":"2023","date_created":"2023-08-22T14:09:47Z","abstract":[{"text":"For the Fröhlich model of the large polaron, we prove that the ground state energy as a function of the total momentum has a unique global minimum at momentum zero. This implies the non-existence of a ground state of the translation invariant Fröhlich Hamiltonian and thus excludes the possibility of a localization transition at finite coupling.","lang":"eng"}],"file":[{"file_id":"14225","relation":"main_file","date_created":"2023-08-23T10:59:15Z","success":1,"file_name":"2023_MathPhysics_Lampart.pdf","date_updated":"2023-08-23T10:59:15Z","file_size":317026,"content_type":"application/pdf","checksum":"f0941cc66cb3ed06a12ca4b7e356cfd6","access_level":"open_access","creator":"dernst"}],"article_type":"original","publication_status":"published","keyword":["Geometry and Topology","Mathematical Physics"],"article_processing_charge":"Yes (via OA deal)","oa_version":"Published Version","quality_controlled":"1"},{"oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication":"arXiv","day":"01","type":"preprint","citation":{"ieee":"S. Löwe, P. Lippe, F. Locatello, and M. Welling, “Rotating features for object discovery,” <i>arXiv</i>. .","apa":"Löwe, S., Lippe, P., Locatello, F., &#38; Welling, M. (n.d.). Rotating features for object discovery. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.2306.00600\">https://doi.org/10.48550/arXiv.2306.00600</a>","ama":"Löwe S, Lippe P, Locatello F, Welling M. Rotating features for object discovery. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.2306.00600\">10.48550/arXiv.2306.00600</a>","mla":"Löwe, Sindy, et al. “Rotating Features for Object Discovery.” <i>ArXiv</i>, 2306.00600, doi:<a href=\"https://doi.org/10.48550/arXiv.2306.00600\">10.48550/arXiv.2306.00600</a>.","ista":"Löwe S, Lippe P, Locatello F, Welling M. Rotating features for object discovery. arXiv, 2306.00600.","chicago":"Löwe, Sindy, Phillip Lippe, Francesco Locatello, and Max Welling. “Rotating Features for Object Discovery.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.2306.00600\">https://doi.org/10.48550/arXiv.2306.00600</a>.","short":"S. Löwe, P. Lippe, F. Locatello, M. Welling, ArXiv (n.d.)."},"author":[{"last_name":"Löwe","first_name":"Sindy","full_name":"Löwe, Sindy"},{"last_name":"Lippe","first_name":"Phillip","full_name":"Lippe, Phillip"},{"last_name":"Locatello","first_name":"Francesco","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4"},{"full_name":"Welling, Max","last_name":"Welling","first_name":"Max"}],"date_updated":"2024-02-12T09:53:44Z","article_number":"2306.00600","status":"public","external_id":{"arxiv":["2306.00600"]},"title":"Rotating features for object discovery","language":[{"iso":"eng"}],"date_published":"2023-06-01T00:00:00Z","doi":"10.48550/arXiv.2306.00600","_id":"14207","year":"2023","date_created":"2023-08-22T14:18:00Z","arxiv":1,"article_processing_charge":"No","oa_version":"Preprint","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2306.00600"}],"abstract":[{"lang":"eng","text":"The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate. Most machine learning efforts addressing this issue in an unsupervised setting have focused on slot-based methods, which may be limiting due to their discrete nature and difficulty to express uncertainty. Recently, the Complex AutoEncoder was proposed as an alternative that learns continuous and distributed object-centric representations. However, it is only applicable to simple toy data. In this paper, we present Rotating Features, a generalization of complex-valued features to higher dimensions, and a new evaluation procedure for extracting objects from distributed representations. Additionally, we show the applicability of our approach to pre-trained features. Together, these advancements enable us to scale distributed object-centric representations from simple toy to real-world data. We believe this work advances a new paradigm for addressing the binding problem in machine learning and has the potential to inspire further innovation in the field."}],"month":"06","department":[{"_id":"FrLo"}],"publication_status":"submitted"},{"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"conference","volume":202,"extern":"1","intvolume":"       202","alternative_title":["PMLR"],"date_published":"2023-05-30T00:00:00Z","status":"public","language":[{"iso":"eng"}],"arxiv":1,"conference":{"name":"International Conference on Machine Learning","location":"Honolulu, Hawaii, United States","start_date":"2023-07-23","end_date":"2023-07-29"},"page":"43105-43128","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2305.19377","open_access":"1"}],"month":"05","department":[{"_id":"FrLo"}],"publisher":"ML Research Press","day":"30","oa":1,"publication":"Proceedings of the 40th International Conference on Machine Learning","citation":{"short":"Z. Zhu, F. Liu, G.G. Chrysos, F. Locatello, V. Cevher, in:, Proceedings of the 40th International Conference on Machine Learning, ML Research Press, 2023, pp. 43105–43128.","ista":"Zhu Z, Liu F, Chrysos GG, Locatello F, Cevher V. 2023. Benign overfitting in deep neural networks under lazy training. Proceedings of the 40th International Conference on Machine Learning. International Conference on Machine Learning, PMLR, vol. 202, 43105–43128.","chicago":"Zhu, Zhenyu, Fanghui Liu, Grigorios G Chrysos, Francesco Locatello, and Volkan Cevher. “Benign Overfitting in Deep Neural Networks under Lazy Training.” In <i>Proceedings of the 40th International Conference on Machine Learning</i>, 202:43105–28. ML Research Press, 2023.","ama":"Zhu Z, Liu F, Chrysos GG, Locatello F, Cevher V. Benign overfitting in deep neural networks under lazy training. In: <i>Proceedings of the 40th International Conference on Machine Learning</i>. Vol 202. ML Research Press; 2023:43105-43128.","ieee":"Z. Zhu, F. Liu, G. G. Chrysos, F. Locatello, and V. Cevher, “Benign overfitting in deep neural networks under lazy training,” in <i>Proceedings of the 40th International Conference on Machine Learning</i>, Honolulu, Hawaii, United States, 2023, vol. 202, pp. 43105–43128.","apa":"Zhu, Z., Liu, F., Chrysos, G. G., Locatello, F., &#38; Cevher, V. (2023). Benign overfitting in deep neural networks under lazy training. In <i>Proceedings of the 40th International Conference on Machine Learning</i> (Vol. 202, pp. 43105–43128). Honolulu, Hawaii, United States: ML Research Press.","mla":"Zhu, Zhenyu, et al. “Benign Overfitting in Deep Neural Networks under Lazy Training.” <i>Proceedings of the 40th International Conference on Machine Learning</i>, vol. 202, ML Research Press, 2023, pp. 43105–28."},"date_updated":"2023-09-13T08:46:46Z","author":[{"full_name":"Zhu, Zhenyu","last_name":"Zhu","first_name":"Zhenyu"},{"last_name":"Liu","first_name":"Fanghui","full_name":"Liu, Fanghui"},{"full_name":"Chrysos, Grigorios G","last_name":"Chrysos","first_name":"Grigorios G"},{"first_name":"Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco"},{"full_name":"Cevher, Volkan","last_name":"Cevher","first_name":"Volkan"}],"external_id":{"arxiv":["2305.19377"]},"title":"Benign overfitting in deep neural networks under lazy training","date_created":"2023-08-22T14:18:18Z","_id":"14208","year":"2023","quality_controlled":"1","article_processing_charge":"No","oa_version":"Preprint","publication_status":"published","abstract":[{"lang":"eng","text":"This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining (nearly) zero-training error under the lazy training regime. For this purpose, we unify three interrelated concepts of overparameterization, benign overfitting, and the Lipschitz constant of DNNs. Our results indicate that interpolating with smoother functions leads to better generalization. Furthermore, we investigate the special case where interpolating smooth ground-truth functions is performed by DNNs under the Neural Tangent Kernel (NTK) regime for generalization. Our result demonstrates that the generalization error converges to a constant order that only depends on label noise and initialization noise, which theoretically verifies benign overfitting. Our analysis provides a tight lower bound on the normalized margin under non-smooth activation functions, as well as the minimum eigenvalue of NTK under high-dimensional settings, which has its own interest in learning theory."}]},{"article_processing_charge":"No","oa_version":"Preprint","main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2304.10253","open_access":"1"}],"abstract":[{"lang":"eng","text":"Diffusion models excel at generating photorealistic images from text-queries. Naturally, many approaches have been proposed to use these generative abilities to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large noisily supervised, but nonetheless, annotated datasets. It is an open question whether the generalization capabilities of diffusion models beyond using the additional data of the pre-training process for augmentation lead to improved downstream performance. We perform a systematic evaluation of existing methods to generate images from diffusion models and study new extensions to assess their benefit for data augmentation. While we find that personalizing diffusion models towards the target data outperforms simpler prompting strategies, we also show that using the training data of the diffusion model alone, via a simple nearest neighbor retrieval procedure, leads to even stronger downstream performance. Overall, our study probes the limitations of diffusion models for data augmentation but also highlights its potential in generating new training data to improve performance on simple downstream vision tasks."}],"month":"04","department":[{"_id":"FrLo"}],"publication_status":"submitted","_id":"14209","year":"2023","date_created":"2023-08-22T14:18:43Z","arxiv":1,"extern":"1","article_number":"2304.10253","title":"A data augmentation perspective on diffusion models and retrieval","status":"public","external_id":{"arxiv":["2304.10253"]},"language":[{"iso":"eng"}],"date_published":"2023-04-20T00:00:00Z","doi":"10.48550/arXiv.2304.10253","oa":1,"publication":"arXiv","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"20","date_updated":"2023-09-13T08:51:56Z","author":[{"full_name":"Burg, Max F.","first_name":"Max F.","last_name":"Burg"},{"full_name":"Wenzel, Florian","first_name":"Florian","last_name":"Wenzel"},{"full_name":"Zietlow, Dominik","last_name":"Zietlow","first_name":"Dominik"},{"last_name":"Horn","first_name":"Max","full_name":"Horn, Max"},{"full_name":"Makansi, Osama","first_name":"Osama","last_name":"Makansi"},{"last_name":"Locatello","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683"},{"last_name":"Russell","first_name":"Chris","full_name":"Russell, Chris"}],"citation":{"short":"M.F. Burg, F. Wenzel, D. Zietlow, M. Horn, O. Makansi, F. Locatello, C. Russell, ArXiv (n.d.).","ista":"Burg MF, Wenzel F, Zietlow D, Horn M, Makansi O, Locatello F, Russell C. A data augmentation perspective on diffusion models and retrieval. arXiv, 2304.10253.","chicago":"Burg, Max F., Florian Wenzel, Dominik Zietlow, Max Horn, Osama Makansi, Francesco Locatello, and Chris Russell. “A Data Augmentation Perspective on Diffusion Models and Retrieval.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.2304.10253\">https://doi.org/10.48550/arXiv.2304.10253</a>.","ieee":"M. F. Burg <i>et al.</i>, “A data augmentation perspective on diffusion models and retrieval,” <i>arXiv</i>. .","ama":"Burg MF, Wenzel F, Zietlow D, et al. A data augmentation perspective on diffusion models and retrieval. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.2304.10253\">10.48550/arXiv.2304.10253</a>","apa":"Burg, M. F., Wenzel, F., Zietlow, D., Horn, M., Makansi, O., Locatello, F., &#38; Russell, C. (n.d.). A data augmentation perspective on diffusion models and retrieval. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.2304.10253\">https://doi.org/10.48550/arXiv.2304.10253</a>","mla":"Burg, Max F., et al. “A Data Augmentation Perspective on Diffusion Models and Retrieval.” <i>ArXiv</i>, 2304.10253, doi:<a href=\"https://doi.org/10.48550/arXiv.2304.10253\">10.48550/arXiv.2304.10253</a>."},"type":"preprint"},{"author":[{"last_name":"Fumero","first_name":"Marco","full_name":"Fumero, Marco"},{"full_name":"Wenzel, Florian","last_name":"Wenzel","first_name":"Florian"},{"first_name":"Luca","last_name":"Zancato","full_name":"Zancato, Luca"},{"full_name":"Achille, Alessandro","first_name":"Alessandro","last_name":"Achille"},{"full_name":"Rodolà, Emanuele","last_name":"Rodolà","first_name":"Emanuele"},{"first_name":"Stefano","last_name":"Soatto","full_name":"Soatto, Stefano"},{"full_name":"Schölkopf, Bernhard","first_name":"Bernhard","last_name":"Schölkopf"},{"orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","last_name":"Locatello"}],"citation":{"mla":"Fumero, Marco, et al. “Leveraging Sparse and Shared Feature Activations for Disentangled Representation Learning.” <i>ArXiv</i>, 2304.07939, doi:<a href=\"https://doi.org/10.48550/arXiv.2304.07939\">10.48550/arXiv.2304.07939</a>.","apa":"Fumero, M., Wenzel, F., Zancato, L., Achille, A., Rodolà, E., Soatto, S., … Locatello, F. (n.d.). Leveraging sparse and shared feature activations for disentangled representation learning. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.2304.07939\">https://doi.org/10.48550/arXiv.2304.07939</a>","ieee":"M. Fumero <i>et al.</i>, “Leveraging sparse and shared feature activations for disentangled representation learning,” <i>arXiv</i>. .","ama":"Fumero M, Wenzel F, Zancato L, et al. Leveraging sparse and shared feature activations for disentangled representation learning. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.2304.07939\">10.48550/arXiv.2304.07939</a>","chicago":"Fumero, Marco, Florian Wenzel, Luca Zancato, Alessandro Achille, Emanuele Rodolà, Stefano Soatto, Bernhard Schölkopf, and Francesco Locatello. “Leveraging Sparse and Shared Feature Activations for Disentangled Representation Learning.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.2304.07939\">https://doi.org/10.48550/arXiv.2304.07939</a>.","ista":"Fumero M, Wenzel F, Zancato L, Achille A, Rodolà E, Soatto S, Schölkopf B, Locatello F. Leveraging sparse and shared feature activations for disentangled representation learning. arXiv, 2304.07939.","short":"M. Fumero, F. Wenzel, L. Zancato, A. Achille, E. Rodolà, S. Soatto, B. Schölkopf, F. Locatello, ArXiv (n.d.)."},"type":"preprint","date_updated":"2024-02-12T09:55:48Z","day":"17","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication":"arXiv","date_published":"2023-04-17T00:00:00Z","doi":"10.48550/arXiv.2304.07939","status":"public","title":"Leveraging sparse and shared feature activations for disentangled representation learning","external_id":{"arxiv":["2304.07939"]},"language":[{"iso":"eng"}],"article_number":"2304.07939","arxiv":1,"date_created":"2023-08-22T14:19:03Z","_id":"14210","year":"2023","month":"04","department":[{"_id":"FrLo"}],"publication_status":"submitted","abstract":[{"text":"Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for representation learning on real world data. In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. Assuming each supervised task only depends on an unknown subset of the factors of variation, we disentangle the feature space of a supervised multi-task model, with features activating sparsely across different tasks and information being shared as appropriate. Importantly, we never directly observe the factors of variations but establish that access to multiple tasks is sufficient for identifiability under sufficiency and minimality assumptions. We validate our approach on six real world distribution shift benchmarks, and different data modalities (images, text), demonstrating how disentangled representations can be transferred to real settings.","lang":"eng"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2304.07939"}],"article_processing_charge":"No","oa_version":"Preprint"},{"arxiv":1,"conference":{"name":"CLeaR: Conference on Causal Learning and Reasoning","start_date":"2023-04-11","location":"Tübingen, Germany","end_date":"2023-04-14"},"date_created":"2023-08-22T14:19:21Z","year":"2023","scopus_import":"1","_id":"14211","department":[{"_id":"FrLo"}],"publication_status":"published","month":"04","abstract":[{"text":"Causal discovery methods are intrinsically constrained by the set of assumptions needed to ensure structure identifiability. Moreover additional restrictions are often imposed in order to simplify the inference task: this is the case for the Gaussian noise assumption on additive non-linear models, which is common to many causal discovery approaches. In this paper we show the shortcomings of inference under this hypothesis, analyzing the risk of edge inversion under violation of Gaussianity of the noise terms. Then, we propose a novel method for inferring the topological ordering of the variables in the causal graph, from data generated according to an additive non-linear model with a generic noise distribution. This leads to NoGAM (Not only Gaussian Additive noise Models), a causal discovery algorithm with a minimal set of assumptions and state of the art performance, experimentally benchmarked on synthetic data.","lang":"eng"}],"quality_controlled":"1","main_file_link":[{"url":"https://arxiv.org/abs/2304.03265","open_access":"1"}],"oa_version":"Preprint","article_processing_charge":"No","type":"conference","date_updated":"2023-09-13T09:00:31Z","citation":{"chicago":"Montagna, Francesco, Nicoletta Noceti, Lorenzo Rosasco, Kun Zhang, and Francesco Locatello. “Causal Discovery with Score Matching on Additive Models with Arbitrary Noise.” In <i>2nd Conference on Causal Learning and Reasoning</i>, 2023.","ista":"Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. 2023. Causal discovery with score matching on additive models with arbitrary noise. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning.","mla":"Montagna, Francesco, et al. “Causal Discovery with Score Matching on Additive Models with Arbitrary Noise.” <i>2nd Conference on Causal Learning and Reasoning</i>, 2023.","ama":"Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. Causal discovery with score matching on additive models with arbitrary noise. In: <i>2nd Conference on Causal Learning and Reasoning</i>. ; 2023.","ieee":"F. Montagna, N. Noceti, L. Rosasco, K. Zhang, and F. Locatello, “Causal discovery with score matching on additive models with arbitrary noise,” in <i>2nd Conference on Causal Learning and Reasoning</i>, Tübingen, Germany, 2023.","apa":"Montagna, F., Noceti, N., Rosasco, L., Zhang, K., &#38; Locatello, F. (2023). Causal discovery with score matching on additive models with arbitrary noise. In <i>2nd Conference on Causal Learning and Reasoning</i>. Tübingen, Germany.","short":"F. Montagna, N. Noceti, L. Rosasco, K. Zhang, F. Locatello, in:, 2nd Conference on Causal Learning and Reasoning, 2023."},"author":[{"full_name":"Montagna, Francesco","first_name":"Francesco","last_name":"Montagna"},{"last_name":"Noceti","first_name":"Nicoletta","full_name":"Noceti, Nicoletta"},{"full_name":"Rosasco, Lorenzo","first_name":"Lorenzo","last_name":"Rosasco"},{"last_name":"Zhang","first_name":"Kun","full_name":"Zhang, Kun"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683","first_name":"Francesco","last_name":"Locatello"}],"day":"01","publication":"2nd Conference on Causal Learning and Reasoning","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa":1,"date_published":"2023-04-01T00:00:00Z","language":[{"iso":"eng"}],"status":"public","external_id":{"arxiv":["2304.03265"]},"title":"Causal discovery with score matching on additive models with arbitrary noise","extern":"1"},{"conference":{"end_date":"2023-04-14","location":"Tübingen, Germany","start_date":"2023-04-11","name":"CLeaR: Conference on Causal Learning and Reasoning"},"arxiv":1,"_id":"14212","scopus_import":"1","year":"2023","date_created":"2023-08-22T14:19:40Z","abstract":[{"text":"This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational non-linear additive Gaussian noise models. Leveraging scalable machine learning approaches to approximate the score function ∇logp(X), we extend the work of Rolland et al. (2022) that only recovers the topological order from the score and requires an expensive pruning step removing spurious edges among those admitted by the ordering. Our analysis leads to DAS (acronym for Discovery At Scale), a practical algorithm that reduces the complexity of the pruning by a factor proportional to the graph size. In practice, DAS achieves competitive accuracy with current state-of-the-art while being over an order of magnitude faster. Overall, our approach enables principled and scalable causal discovery, significantly lowering the compute bar.","lang":"eng"}],"month":"04","publication_status":"published","department":[{"_id":"FrLo"}],"article_processing_charge":"No","oa_version":"Preprint","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2304.03382"}],"quality_controlled":"1","type":"conference","citation":{"short":"F. Montagna, N. Noceti, L. Rosasco, K. Zhang, F. Locatello, in:, 2nd Conference on Causal Learning and Reasoning, 2023.","chicago":"Montagna, Francesco, Nicoletta Noceti, Lorenzo Rosasco, Kun Zhang, and Francesco Locatello. “Scalable Causal Discovery with Score Matching.” In <i>2nd Conference on Causal Learning and Reasoning</i>, 2023.","ista":"Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. 2023. Scalable causal discovery with score matching. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning.","mla":"Montagna, Francesco, et al. “Scalable Causal Discovery with Score Matching.” <i>2nd Conference on Causal Learning and Reasoning</i>, 2023.","ieee":"F. Montagna, N. Noceti, L. Rosasco, K. Zhang, and F. Locatello, “Scalable causal discovery with score matching,” in <i>2nd Conference on Causal Learning and Reasoning</i>, Tübingen, Germany, 2023.","ama":"Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. Scalable causal discovery with score matching. In: <i>2nd Conference on Causal Learning and Reasoning</i>. ; 2023.","apa":"Montagna, F., Noceti, N., Rosasco, L., Zhang, K., &#38; Locatello, F. (2023). Scalable causal discovery with score matching. In <i>2nd Conference on Causal Learning and Reasoning</i>. Tübingen, Germany."},"author":[{"last_name":"Montagna","first_name":"Francesco","full_name":"Montagna, Francesco"},{"full_name":"Noceti, Nicoletta","last_name":"Noceti","first_name":"Nicoletta"},{"full_name":"Rosasco, Lorenzo","first_name":"Lorenzo","last_name":"Rosasco"},{"first_name":"Kun","last_name":"Zhang","full_name":"Zhang, Kun"},{"orcid":"0000-0002-4850-0683","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","first_name":"Francesco","last_name":"Locatello"}],"date_updated":"2023-09-13T09:03:24Z","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication":"2nd Conference on Causal Learning and Reasoning","day":"01","external_id":{"arxiv":["2304.03382"]},"status":"public","title":"Scalable causal discovery with score matching","language":[{"iso":"eng"}],"date_published":"2023-04-01T00:00:00Z","extern":"1"},{"day":"12","oa":1,"publication":"2nd Conference on Causal Learning and Reasoning","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_updated":"2023-09-13T09:23:08Z","author":[{"full_name":"Liu, Yuejiang","first_name":"Yuejiang","last_name":"Liu"},{"full_name":"Alahi, Alexandre","first_name":"Alexandre","last_name":"Alahi"},{"first_name":"Chris","last_name":"Russell","full_name":"Russell, Chris"},{"last_name":"Horn","first_name":"Max","full_name":"Horn, Max"},{"first_name":"Dominik","last_name":"Zietlow","full_name":"Zietlow, Dominik"},{"last_name":"Schölkopf","first_name":"Bernhard","full_name":"Schölkopf, Bernhard"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco"}],"type":"conference","citation":{"mla":"Liu, Yuejiang, et al. “Causal Triplet: An Open Challenge for Intervention-Centric Causal Representation Learning.” <i>2nd Conference on Causal Learning and Reasoning</i>, 2023.","ieee":"Y. Liu <i>et al.</i>, “Causal triplet: An open challenge for intervention-centric causal representation learning,” in <i>2nd Conference on Causal Learning and Reasoning</i>, Tübingen, Germany, 2023.","apa":"Liu, Y., Alahi, A., Russell, C., Horn, M., Zietlow, D., Schölkopf, B., &#38; Locatello, F. (2023). Causal triplet: An open challenge for intervention-centric causal representation learning. In <i>2nd Conference on Causal Learning and Reasoning</i>. Tübingen, Germany.","ama":"Liu Y, Alahi A, Russell C, et al. Causal triplet: An open challenge for intervention-centric causal representation learning. In: <i>2nd Conference on Causal Learning and Reasoning</i>. ; 2023.","chicago":"Liu, Yuejiang, Alexandre Alahi, Chris Russell, Max Horn, Dominik Zietlow, Bernhard Schölkopf, and Francesco Locatello. “Causal Triplet: An Open Challenge for Intervention-Centric Causal Representation Learning.” In <i>2nd Conference on Causal Learning and Reasoning</i>, 2023.","ista":"Liu Y, Alahi A, Russell C, Horn M, Zietlow D, Schölkopf B, Locatello F. 2023. Causal triplet: An open challenge for intervention-centric causal representation learning. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning.","short":"Y. Liu, A. Alahi, C. Russell, M. Horn, D. Zietlow, B. Schölkopf, F. Locatello, in:, 2nd Conference on Causal Learning and Reasoning, 2023."},"extern":"1","date_published":"2023-04-12T00:00:00Z","status":"public","title":"Causal triplet: An open challenge for intervention-centric causal representation learning","external_id":{"arxiv":["2301.05169"]},"language":[{"iso":"eng"}],"date_created":"2023-08-22T14:20:18Z","_id":"14214","year":"2023","arxiv":1,"conference":{"end_date":"2023-04-14","location":"Tübingen, Germany","start_date":"2023-04-11","name":"CLeaR: Conference on Causal Learning and Reasoning"},"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2301.05169"}],"quality_controlled":"1","article_processing_charge":"No","oa_version":"Preprint","month":"04","department":[{"_id":"FrLo"}],"publication_status":"published","abstract":[{"lang":"eng","text":"Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In this paper, we present Causal Triplet, a causal representation learning benchmark featuring not only visually more complex scenes, but also two crucial desiderata commonly overlooked in previous works: (i) an actionable counterfactual setting, where only certain object-level variables allow for counterfactual observations whereas others do not; (ii) an interventional downstream task with an emphasis on out-of-distribution robustness from the independent causal mechanisms principle. Through extensive experiments, we find that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts. However, recent causal representation learning methods still struggle to identify such latent structures, indicating substantial challenges and opportunities for future work."}]},{"date_created":"2023-08-22T14:22:20Z","year":"2023","_id":"14217","arxiv":1,"conference":{"start_date":"2023-05-01","name":"International Conference on Machine Learning Representations","location":"Kigali, Rwanda","end_date":"2023-05-05"},"quality_controlled":"1","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2209.15430"}],"oa_version":"Preprint","article_processing_charge":"No","department":[{"_id":"FrLo"}],"publication_status":"published","month":"05","abstract":[{"text":"Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. Ideally, the distribution of the data points in the latent space should depend only on the task, the data, the loss, and other architecture-specific constraints. However, factors such as the random weights initialization, training hyperparameters, or other sources of randomness in the training phase may induce incoherent latent spaces that hinder any form of reuse. Nevertheless, we empirically observe that, under the same data and modeling choices, the angles between the encodings within distinct latent spaces do not change. In this work, we propose the latent similarity between each sample and a fixed set of anchors as an alternative data representation, demonstrating that it can enforce the desired invariances without any additional training. We show how neural architectures can leverage these relative representations to guarantee, in practice, invariance to latent isometries and rescalings, effectively enabling latent space communication: from zero-shot model stitching to latent space comparison between diverse settings. We extensively validate the generalization capability of our approach on different datasets, spanning various modalities (images, text, graphs), tasks (e.g., classification, reconstruction) and architectures (e.g., CNNs, GCNs, transformers).","lang":"eng"}],"day":"01","publication":"The 11th International Conference on Learning Representations","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa":1,"date_updated":"2023-09-13T09:44:26Z","type":"conference","author":[{"full_name":"Moschella, Luca","last_name":"Moschella","first_name":"Luca"},{"full_name":"Maiorca, Valentino","last_name":"Maiorca","first_name":"Valentino"},{"full_name":"Fumero, Marco","first_name":"Marco","last_name":"Fumero"},{"full_name":"Norelli, Antonio","last_name":"Norelli","first_name":"Antonio"},{"first_name":"Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4"},{"last_name":"Rodolà","first_name":"Emanuele","full_name":"Rodolà, Emanuele"}],"citation":{"short":"L. Moschella, V. Maiorca, M. Fumero, A. Norelli, F. Locatello, E. Rodolà, in:, The 11th International Conference on Learning Representations, 2023.","chicago":"Moschella, Luca, Valentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, and Emanuele Rodolà. “Relative Representations Enable Zero-Shot Latent Space Communication.” In <i>The 11th International Conference on Learning Representations</i>, 2023.","ista":"Moschella L, Maiorca V, Fumero M, Norelli A, Locatello F, Rodolà E. 2023. Relative representations enable zero-shot latent space communication. The 11th International Conference on Learning Representations. International Conference on Machine Learning Representations.","mla":"Moschella, Luca, et al. “Relative Representations Enable Zero-Shot Latent Space Communication.” <i>The 11th International Conference on Learning Representations</i>, 2023.","ieee":"L. Moschella, V. Maiorca, M. Fumero, A. Norelli, F. Locatello, and E. Rodolà, “Relative representations enable zero-shot latent space communication,” in <i>The 11th International Conference on Learning Representations</i>, Kigali, Rwanda, 2023.","ama":"Moschella L, Maiorca V, Fumero M, Norelli A, Locatello F, Rodolà E. Relative representations enable zero-shot latent space communication. In: <i>The 11th International Conference on Learning Representations</i>. ; 2023.","apa":"Moschella, L., Maiorca, V., Fumero, M., Norelli, A., Locatello, F., &#38; Rodolà, E. (2023). Relative representations enable zero-shot latent space communication. In <i>The 11th International Conference on Learning Representations</i>. Kigali, Rwanda."},"extern":"1","date_published":"2023-05-01T00:00:00Z","language":[{"iso":"eng"}],"title":"Relative representations enable zero-shot latent space communication","status":"public","external_id":{"arxiv":["2209.15430"]}},{"article_processing_charge":"No","oa_version":"Preprint","main_file_link":[{"url":"https://arxiv.org/abs/2209.14860","open_access":"1"}],"quality_controlled":"1","abstract":[{"text":"Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing image-based object-centric learning models on simulated data and is the first unsupervised object-centric model that scales to real-world datasets such as COCO and PASCAL VOC. DINOSAUR is conceptually simple and shows competitive performance compared to more involved pipelines from the computer vision literature.","lang":"eng"}],"month":"05","publication_status":"published","department":[{"_id":"FrLo"}],"_id":"14218","year":"2023","date_created":"2023-08-22T14:22:41Z","conference":{"end_date":"2023-05-05","start_date":"2023-05-01","location":"Kigali, Rwanda","name":"ICLR: International Conference on Learning Representations"},"arxiv":1,"extern":"1","external_id":{"arxiv":["2209.14860"]},"status":"public","title":"Bridging the gap to real-world object-centric learning","language":[{"iso":"eng"}],"date_published":"2023-05-10T00:00:00Z","oa":1,"publication":"The 11th International Conference on Learning Representations","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"10","type":"conference","citation":{"chicago":"Seitzer, Maximilian, Max Horn, Andrii Zadaianchuk, Dominik Zietlow, Tianjun Xiao, Carl-Johann Simon-Gabriel Carl-Johann Simon-Gabriel, Tong He, et al. “Bridging the Gap to Real-World Object-Centric Learning.” In <i>The 11th International Conference on Learning Representations</i>, 2023.","ista":"Seitzer M, Horn M, Zadaianchuk A, Zietlow D, Xiao T, Carl-Johann Simon-Gabriel C-JS-G, He T, Zhang Z, Schölkopf B, Brox T, Locatello F. 2023. Bridging the gap to real-world object-centric learning. The 11th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.","mla":"Seitzer, Maximilian, et al. “Bridging the Gap to Real-World Object-Centric Learning.” <i>The 11th International Conference on Learning Representations</i>, 2023.","apa":"Seitzer, M., Horn, M., Zadaianchuk, A., Zietlow, D., Xiao, T., Carl-Johann Simon-Gabriel, C.-J. S.-G., … Locatello, F. (2023). Bridging the gap to real-world object-centric learning. In <i>The 11th International Conference on Learning Representations</i>. Kigali, Rwanda.","ama":"Seitzer M, Horn M, Zadaianchuk A, et al. Bridging the gap to real-world object-centric learning. In: <i>The 11th International Conference on Learning Representations</i>. ; 2023.","ieee":"M. Seitzer <i>et al.</i>, “Bridging the gap to real-world object-centric learning,” in <i>The 11th International Conference on Learning Representations</i>, Kigali, Rwanda, 2023.","short":"M. Seitzer, M. Horn, A. Zadaianchuk, D. Zietlow, T. Xiao, C.-J.S.-G. Carl-Johann Simon-Gabriel, T. He, Z. Zhang, B. Schölkopf, T. Brox, F. Locatello, in:, The 11th International Conference on Learning Representations, 2023."},"author":[{"last_name":"Seitzer","first_name":"Maximilian","full_name":"Seitzer, Maximilian"},{"last_name":"Horn","first_name":"Max","full_name":"Horn, Max"},{"full_name":"Zadaianchuk, Andrii","first_name":"Andrii","last_name":"Zadaianchuk"},{"last_name":"Zietlow","first_name":"Dominik","full_name":"Zietlow, Dominik"},{"first_name":"Tianjun","last_name":"Xiao","full_name":"Xiao, Tianjun"},{"first_name":"Carl-Johann Simon-Gabriel","last_name":"Carl-Johann Simon-Gabriel","full_name":"Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel"},{"last_name":"He","first_name":"Tong","full_name":"He, Tong"},{"full_name":"Zhang, Zheng","first_name":"Zheng","last_name":"Zhang"},{"full_name":"Schölkopf, Bernhard","last_name":"Schölkopf","first_name":"Bernhard"},{"full_name":"Brox, Thomas","last_name":"Brox","first_name":"Thomas"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco"}],"date_updated":"2023-09-13T11:37:03Z"},{"author":[{"full_name":"Zadaianchuk, Andrii","last_name":"Zadaianchuk","first_name":"Andrii"},{"full_name":"Kleindessner, Matthaeus","last_name":"Kleindessner","first_name":"Matthaeus"},{"last_name":"Zhu","first_name":"Yi","full_name":"Zhu, Yi"},{"first_name":"Francesco","last_name":"Locatello","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683"},{"first_name":"Thomas","last_name":"Brox","full_name":"Brox, Thomas"}],"citation":{"short":"A. Zadaianchuk, M. Kleindessner, Y. Zhu, F. Locatello, T. Brox, in:, The 11th International Conference on Learning Representations, 2023.","mla":"Zadaianchuk, Andrii, et al. “Unsupervised Semantic Segmentation with Self-Supervised Object-Centric Representations.” <i>The 11th International Conference on Learning Representations</i>, 2023.","apa":"Zadaianchuk, A., Kleindessner, M., Zhu, Y., Locatello, F., &#38; Brox, T. (2023). Unsupervised semantic segmentation with self-supervised object-centric representations. In <i>The 11th International Conference on Learning Representations</i>. Kigali, Rwanda.","ama":"Zadaianchuk A, Kleindessner M, Zhu Y, Locatello F, Brox T. Unsupervised semantic segmentation with self-supervised object-centric representations. In: <i>The 11th International Conference on Learning Representations</i>. ; 2023.","ieee":"A. Zadaianchuk, M. Kleindessner, Y. Zhu, F. Locatello, and T. Brox, “Unsupervised semantic segmentation with self-supervised object-centric representations,” in <i>The 11th International Conference on Learning Representations</i>, Kigali, Rwanda, 2023.","chicago":"Zadaianchuk, Andrii, Matthaeus Kleindessner, Yi Zhu, Francesco Locatello, and Thomas Brox. “Unsupervised Semantic Segmentation with Self-Supervised Object-Centric Representations.” In <i>The 11th International Conference on Learning Representations</i>, 2023.","ista":"Zadaianchuk A, Kleindessner M, Zhu Y, Locatello F, Brox T. 2023. Unsupervised semantic segmentation with self-supervised object-centric representations. The 11th International Conference on Learning Representations. ICLR: International Conference on Learning Representations."},"date_updated":"2023-09-13T11:25:43Z","type":"conference","oa":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication":"The 11th International Conference on Learning Representations","day":"01","title":"Unsupervised semantic segmentation with self-supervised object-centric representations","status":"public","external_id":{"arxiv":["2207.05027"]},"language":[{"iso":"eng"}],"date_published":"2023-05-01T00:00:00Z","extern":"1","conference":{"start_date":"2023-05-01","location":"Kigali, Rwanda","name":"ICLR: International Conference on Learning Representations","end_date":"2023-05-05"},"arxiv":1,"_id":"14219","year":"2023","date_created":"2023-08-22T14:22:58Z","abstract":[{"lang":"eng","text":"In this paper, we show that recent advances in self-supervised feature\r\nlearning enable unsupervised object discovery and semantic segmentation with a\r\nperformance that matches the state of the field on supervised semantic\r\nsegmentation 10 years ago. We propose a methodology based on unsupervised\r\nsaliency masks and self-supervised feature clustering to kickstart object\r\ndiscovery followed by training a semantic segmentation network on pseudo-labels\r\nto bootstrap the system on images with multiple objects. We present results on\r\nPASCAL VOC that go far beyond the current state of the art (50.0 mIoU), and we\r\nreport for the first time results on MS COCO for the whole set of 81 classes:\r\nour method discovers 34 categories with more than $20\\%$ IoU, while obtaining\r\nan average IoU of 19.6 for all 81 categories."}],"month":"05","publication_status":"published","department":[{"_id":"FrLo"}],"article_processing_charge":"No","oa_version":"Preprint","main_file_link":[{"url":"https://arxiv.org/abs/2207.05027","open_access":"1"}],"quality_controlled":"1"},{"citation":{"ama":"Tangemann M, Schneider S, Kügelgen J von, et al. Unsupervised object learning via common fate. In: <i>2nd Conference on Causal Learning and Reasoning</i>. ; 2023.","ieee":"M. Tangemann <i>et al.</i>, “Unsupervised object learning via common fate,” in <i>2nd Conference on Causal Learning and Reasoning</i>, Tübingen, Germany, 2023.","apa":"Tangemann, M., Schneider, S., Kügelgen, J. von, Locatello, F., Gehler, P., Brox, T., … Schölkopf, B. (2023). Unsupervised object learning via common fate. In <i>2nd Conference on Causal Learning and Reasoning</i>. Tübingen, Germany.","mla":"Tangemann, Matthias, et al. “Unsupervised Object Learning via Common Fate.” <i>2nd Conference on Causal Learning and Reasoning</i>, 2110.06562, 2023.","ista":"Tangemann M, Schneider S, Kügelgen J von, Locatello F, Gehler P, Brox T, Kümmerer M, Bethge M, Schölkopf B. 2023. Unsupervised object learning via common fate. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning, 2110.06562.","chicago":"Tangemann, Matthias, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, and Bernhard Schölkopf. “Unsupervised Object Learning via Common Fate.” In <i>2nd Conference on Causal Learning and Reasoning</i>, 2023.","short":"M. Tangemann, S. Schneider, J. von Kügelgen, F. Locatello, P. Gehler, T. Brox, M. Kümmerer, M. Bethge, B. Schölkopf, in:, 2nd Conference on Causal Learning and Reasoning, 2023."},"date_updated":"2023-09-13T11:31:14Z","type":"conference","author":[{"full_name":"Tangemann, Matthias","last_name":"Tangemann","first_name":"Matthias"},{"full_name":"Schneider, Steffen","first_name":"Steffen","last_name":"Schneider"},{"full_name":"Kügelgen, Julius von","last_name":"Kügelgen","first_name":"Julius von"},{"last_name":"Locatello","first_name":"Francesco","orcid":"0000-0002-4850-0683","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco"},{"first_name":"Peter","last_name":"Gehler","full_name":"Gehler, Peter"},{"full_name":"Brox, Thomas","last_name":"Brox","first_name":"Thomas"},{"full_name":"Kümmerer, Matthias","first_name":"Matthias","last_name":"Kümmerer"},{"first_name":"Matthias","last_name":"Bethge","full_name":"Bethge, Matthias"},{"first_name":"Bernhard","last_name":"Schölkopf","full_name":"Schölkopf, Bernhard"}],"oa":1,"publication":"2nd Conference on Causal Learning and Reasoning","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","day":"15","title":"Unsupervised object learning via common fate","external_id":{"arxiv":["2110.06562"]},"status":"public","language":[{"iso":"eng"}],"date_published":"2023-04-15T00:00:00Z","extern":"1","article_number":"2110.06562","conference":{"end_date":"2023-04-14","start_date":"2023-04-11","location":"Tübingen, Germany","name":"CLeaR: Conference on Causal Learning and Reasoning"},"arxiv":1,"_id":"14222","year":"2023","date_created":"2023-08-22T14:23:54Z","abstract":[{"lang":"eng","text":"Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling. We decompose this problem into three easier subtasks, and provide candidate solutions for each of them. Inspired by the Common Fate Principle of Gestalt Psychology, we first extract (noisy) masks of moving objects via unsupervised motion segmentation. Second, generative models are trained on the masks of the background and the moving objects, respectively. Third, background and foreground models are combined in a conditional \"dead leaves\" scene model to sample novel scene configurations where occlusions and depth layering arise naturally. To evaluate the individual stages, we introduce the Fishbowl dataset positioned between complex real-world scenes and common object-centric benchmarks of simplistic objects. We show that our approach allows learning generative models that generalize beyond the occlusions present in the input videos, and represent scenes in a modular fashion that allows sampling plausible scenes outside the training distribution by permitting, for instance, object numbers or densities not observed in the training set."}],"month":"04","department":[{"_id":"FrLo"}],"publication_status":"published","article_processing_charge":"No","oa_version":"Preprint","main_file_link":[{"url":"https://arxiv.org/abs/2110.06562","open_access":"1"}],"quality_controlled":"1"},{"page":"43","degree_awarded":"MS","month":"08","publisher":"Institute of Science and Technology Austria","department":[{"_id":"GradSch"},{"_id":"HeEd"}],"file_date_updated":"2024-02-26T23:30:03Z","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","type":"dissertation","ddc":["500"],"alternative_title":["ISTA Master's Thesis"],"date_published":"2023-08-24T00:00:00Z","doi":"10.15479/at:ista:14226","status":"public","language":[{"iso":"eng"}],"date_created":"2023-08-24T13:01:18Z","_id":"14226","year":"2023","article_processing_charge":"No","oa_version":"Published Version","publication_status":"published","abstract":[{"text":"We introduce the notion of a Faustian interchange in a 1-parameter family of smooth\r\nfunctions to generalize the medial axis to critical points of index larger than 0.\r\nWe construct and implement a general purpose algorithm for approximating such\r\ngeneralized medial axes.","lang":"eng"}],"file":[{"date_updated":"2024-02-26T23:30:03Z","embargo_to":"open_access","file_name":"documents-export-2023-08-24.zip","date_created":"2023-08-24T13:02:49Z","relation":"source_file","file_id":"14227","creator":"cchlebak","access_level":"closed","checksum":"453caf851d75c3478c10ed09bd242a91","file_size":15501411,"content_type":"application/x-zip-compressed"},{"access_level":"open_access","creator":"cchlebak","checksum":"7349d29963d6695e555e171748648d9a","content_type":"application/pdf","file_size":6854783,"date_updated":"2024-02-26T23:30:03Z","embargo":"2024-02-25","file_name":"thesis_pdf_a.pdf","file_id":"14228","date_created":"2023-08-24T13:03:42Z","relation":"main_file"}],"day":"24","oa":1,"publication_identifier":{"issn":["2791-4585"]},"citation":{"chicago":"Stephenson, Elizabeth R. “Generalizing Medial Axes with Homology Switches.” Institute of Science and Technology Austria, 2023. <a href=\"https://doi.org/10.15479/at:ista:14226\">https://doi.org/10.15479/at:ista:14226</a>.","ista":"Stephenson ER. 2023. Generalizing medial axes with homology switches. Institute of Science and Technology Austria.","mla":"Stephenson, Elizabeth R. <i>Generalizing Medial Axes with Homology Switches</i>. Institute of Science and Technology Austria, 2023, doi:<a href=\"https://doi.org/10.15479/at:ista:14226\">10.15479/at:ista:14226</a>.","ama":"Stephenson ER. Generalizing medial axes with homology switches. 2023. doi:<a href=\"https://doi.org/10.15479/at:ista:14226\">10.15479/at:ista:14226</a>","ieee":"E. R. Stephenson, “Generalizing medial axes with homology switches,” Institute of Science and Technology Austria, 2023.","apa":"Stephenson, E. R. (2023). <i>Generalizing medial axes with homology switches</i>. Institute of Science and Technology Austria. <a href=\"https://doi.org/10.15479/at:ista:14226\">https://doi.org/10.15479/at:ista:14226</a>","short":"E.R. Stephenson, Generalizing Medial Axes with Homology Switches, Institute of Science and Technology Austria, 2023."},"author":[{"id":"2D04F932-F248-11E8-B48F-1D18A9856A87","full_name":"Stephenson, Elizabeth R","orcid":"0000-0002-6862-208X","first_name":"Elizabeth R","last_name":"Stephenson"}],"date_updated":"2024-02-26T23:30:04Z","supervisor":[{"id":"3FB178DA-F248-11E8-B48F-1D18A9856A87","full_name":"Edelsbrunner, Herbert","orcid":"0000-0002-9823-6833","first_name":"Herbert","last_name":"Edelsbrunner"}],"has_accepted_license":"1","title":"Generalizing medial axes with homology switches"},{"article_number":"053201","issue":"5","project":[{"name":"Angulon: physics and applications of a new quasiparticle","grant_number":"801770","call_identifier":"H2020","_id":"2688CF98-B435-11E9-9278-68D0E5697425"}],"external_id":{"arxiv":["2308.15247"],"pmid":["37595218"],"isi":["001101784100001"]},"title":"Nonadiabatic laser-induced alignment dynamics of molecules on a surface","day":"04","publication_identifier":{"issn":["0031-9007"],"eissn":["1079-7114"]},"publication":"Physical Review Letters","oa":1,"author":[{"full_name":"Kranabetter, Lorenz","last_name":"Kranabetter","first_name":"Lorenz"},{"full_name":"Kristensen, Henrik H.","first_name":"Henrik H.","last_name":"Kristensen"},{"last_name":"Ghazaryan","first_name":"Areg","orcid":"0000-0001-9666-3543","full_name":"Ghazaryan, Areg","id":"4AF46FD6-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Schouder","first_name":"Constant A.","full_name":"Schouder, Constant A."},{"last_name":"Chatterley","first_name":"Adam S.","full_name":"Chatterley, Adam S."},{"full_name":"Janssen, Paul","first_name":"Paul","last_name":"Janssen"},{"full_name":"Jensen, Frank","first_name":"Frank","last_name":"Jensen"},{"first_name":"Robert E.","last_name":"Zillich","full_name":"Zillich, Robert E."},{"first_name":"Mikhail","last_name":"Lemeshko","id":"37CB05FA-F248-11E8-B48F-1D18A9856A87","full_name":"Lemeshko, Mikhail","orcid":"0000-0002-6990-7802"},{"full_name":"Stapelfeldt, Henrik","last_name":"Stapelfeldt","first_name":"Henrik"}],"date_updated":"2023-12-13T12:18:54Z","citation":{"chicago":"Kranabetter, Lorenz, Henrik H. Kristensen, Areg Ghazaryan, Constant A. Schouder, Adam S. Chatterley, Paul Janssen, Frank Jensen, Robert E. Zillich, Mikhail Lemeshko, and Henrik Stapelfeldt. “Nonadiabatic Laser-Induced Alignment Dynamics of Molecules on a Surface.” <i>Physical Review Letters</i>. American Physical Society, 2023. <a href=\"https://doi.org/10.1103/PhysRevLett.131.053201\">https://doi.org/10.1103/PhysRevLett.131.053201</a>.","ista":"Kranabetter L, Kristensen HH, Ghazaryan A, Schouder CA, Chatterley AS, Janssen P, Jensen F, Zillich RE, Lemeshko M, Stapelfeldt H. 2023. Nonadiabatic laser-induced alignment dynamics of molecules on a surface. Physical Review Letters. 131(5), 053201.","mla":"Kranabetter, Lorenz, et al. “Nonadiabatic Laser-Induced Alignment Dynamics of Molecules on a Surface.” <i>Physical Review Letters</i>, vol. 131, no. 5, 053201, American Physical Society, 2023, doi:<a href=\"https://doi.org/10.1103/PhysRevLett.131.053201\">10.1103/PhysRevLett.131.053201</a>.","apa":"Kranabetter, L., Kristensen, H. H., Ghazaryan, A., Schouder, C. A., Chatterley, A. S., Janssen, P., … Stapelfeldt, H. (2023). Nonadiabatic laser-induced alignment dynamics of molecules on a surface. <i>Physical Review Letters</i>. American Physical Society. <a href=\"https://doi.org/10.1103/PhysRevLett.131.053201\">https://doi.org/10.1103/PhysRevLett.131.053201</a>","ama":"Kranabetter L, Kristensen HH, Ghazaryan A, et al. Nonadiabatic laser-induced alignment dynamics of molecules on a surface. <i>Physical Review Letters</i>. 2023;131(5). doi:<a href=\"https://doi.org/10.1103/PhysRevLett.131.053201\">10.1103/PhysRevLett.131.053201</a>","ieee":"L. Kranabetter <i>et al.</i>, “Nonadiabatic laser-induced alignment dynamics of molecules on a surface,” <i>Physical Review Letters</i>, vol. 131, no. 5. American Physical Society, 2023.","short":"L. Kranabetter, H.H. Kristensen, A. Ghazaryan, C.A. Schouder, A.S. Chatterley, P. Janssen, F. Jensen, R.E. Zillich, M. Lemeshko, H. Stapelfeldt, Physical Review Letters 131 (2023)."},"quality_controlled":"1","oa_version":"Preprint","article_processing_charge":"No","article_type":"original","publication_status":"published","abstract":[{"text":"We demonstrate that a sodium dimer, Na2(13Σ+u), residing on the surface of a helium nanodroplet, can be set into rotation by a nonresonant 1.0 ps infrared laser pulse. The time-dependent degree of alignment measured, exhibits a periodic, gradually decreasing structure that deviates qualitatively from that expected for gas-phase dimers. Comparison to alignment dynamics calculated from the time-dependent rotational Schrödinger equation shows that the deviation is due to the alignment dependent interaction between the dimer and the droplet surface. This interaction confines the dimer to the tangential plane of the droplet surface at the point where it resides and is the reason that the observed alignment dynamics is also well described by a 2D quantum rotor model.","lang":"eng"}],"date_created":"2023-08-27T22:01:16Z","pmid":1,"ec_funded":1,"year":"2023","_id":"14238","intvolume":"       131","doi":"10.1103/PhysRevLett.131.053201","date_published":"2023-08-04T00:00:00Z","language":[{"iso":"eng"}],"status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"journal_article","volume":131,"isi":1,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2308.15247","open_access":"1"}],"publisher":"American Physical Society","department":[{"_id":"MiLe"}],"month":"08","acknowledgement":"H. S. acknowledges support from The Villum Foundation through a Villum Investigator Grant No. 25886. M. L. acknowledges support by the European Research Council (ERC) Starting Grant No. 801770 (ANGULON). F. J. and R. E. Z. acknowledge support from the Centre for Scientific Computing, Aarhus and the JKU scientific computing administration, Linz, respectively.","scopus_import":"1","arxiv":1},{"file":[{"file_id":"14266","success":1,"date_created":"2023-09-05T06:43:11Z","relation":"main_file","file_name":"2023_ForumMathematics_Mauri.pdf","date_updated":"2023-09-05T06:43:11Z","file_size":280865,"content_type":"application/pdf","checksum":"c36241750cc5cb06890aec0ecdfee626","access_level":"open_access","creator":"dernst"}],"abstract":[{"text":"Given a resolution of rational singularities  π:X~→X  over a field of characteristic zero, we use a Hodge-theoretic argument to prove that the image of the functor  Rπ∗:Db(X~)→Db(X)\r\n  between bounded derived categories of coherent sheaves generates  Db(X)\r\n  as a triangulated category. This gives a weak version of the Bondal–Orlov localization conjecture [BO02], answering a question from [PS21]. The same result is established more generally for proper (not necessarily birational) morphisms  π:X~→X , with  X~\r\n  smooth, satisfying  Rπ∗(OX~)=OX .","lang":"eng"}],"article_type":"original","publication_status":"published","oa_version":"Published Version","article_processing_charge":"Yes","quality_controlled":"1","year":"2023","_id":"14239","ec_funded":1,"date_created":"2023-08-27T22:01:16Z","project":[{"name":"IST-BRIDGE: International postdoctoral program","grant_number":"101034413","_id":"fc2ed2f7-9c52-11eb-aca3-c01059dda49c","call_identifier":"H2020"}],"title":"Homological Bondal-Orlov localization conjecture for rational singularities","external_id":{"isi":["001041926700001"],"arxiv":["2212.06786"]},"article_number":"e66","has_accepted_license":"1","date_updated":"2023-12-13T12:18:18Z","author":[{"id":"2cf70c34-09c1-11ed-bd8d-c34fac206130","full_name":"Mauri, Mirko","last_name":"Mauri","first_name":"Mirko"},{"first_name":"Evgeny","last_name":"Shinder","full_name":"Shinder, Evgeny"}],"citation":{"mla":"Mauri, Mirko, and Evgeny Shinder. “Homological Bondal-Orlov Localization Conjecture for Rational Singularities.” <i>Forum of Mathematics, Sigma</i>, vol. 11, e66, Cambridge University Press, 2023, doi:<a href=\"https://doi.org/10.1017/fms.2023.65\">10.1017/fms.2023.65</a>.","ama":"Mauri M, Shinder E. Homological Bondal-Orlov localization conjecture for rational singularities. <i>Forum of Mathematics, Sigma</i>. 2023;11. doi:<a href=\"https://doi.org/10.1017/fms.2023.65\">10.1017/fms.2023.65</a>","apa":"Mauri, M., &#38; Shinder, E. (2023). Homological Bondal-Orlov localization conjecture for rational singularities. <i>Forum of Mathematics, Sigma</i>. Cambridge University Press. <a href=\"https://doi.org/10.1017/fms.2023.65\">https://doi.org/10.1017/fms.2023.65</a>","ieee":"M. Mauri and E. Shinder, “Homological Bondal-Orlov localization conjecture for rational singularities,” <i>Forum of Mathematics, Sigma</i>, vol. 11. Cambridge University Press, 2023.","chicago":"Mauri, Mirko, and Evgeny Shinder. “Homological Bondal-Orlov Localization Conjecture for Rational Singularities.” <i>Forum of Mathematics, Sigma</i>. Cambridge University Press, 2023. <a href=\"https://doi.org/10.1017/fms.2023.65\">https://doi.org/10.1017/fms.2023.65</a>.","ista":"Mauri M, Shinder E. 2023. Homological Bondal-Orlov localization conjecture for rational singularities. Forum of Mathematics, Sigma. 11, e66.","short":"M. Mauri, E. Shinder, Forum of Mathematics, Sigma 11 (2023)."},"publication_identifier":{"eissn":["2050-5094"]},"publication":"Forum of Mathematics, Sigma","oa":1,"day":"03","publisher":"Cambridge University Press","department":[{"_id":"TaHa"}],"month":"08","isi":1,"arxiv":1,"scopus_import":"1","acknowledgement":"We thank Agnieszka Bodzenta-Skibińska, Paolo Cascini, Wahei Hara, Sándor Kovács, Alexander Kuznetsov, Mircea Musta  ă, Nebojsa Pavic, Pavel Sechin, and Michael Wemyss for discussions and e-mail correspondence. We also thank the anonymous referee for the helpful comments. M.M. was supported by the Institute of Science and Technology Austria. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no. 101034413. E.S. was partially supported by the EPSRC grant EP/T019379/1 “Derived categories and algebraic K-theory of singularities”, and by the ERC Synergy grant “Modern Aspects of Geometry: Categories, Cycles and Cohomology of Hyperkähler Varieties.”\r\n\r\n","language":[{"iso":"eng"}],"tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"status":"public","doi":"10.1017/fms.2023.65","date_published":"2023-08-03T00:00:00Z","intvolume":"        11","ddc":["510"],"volume":11,"type":"journal_article","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","file_date_updated":"2023-09-05T06:43:11Z"},{"acknowledgement":"We thank Georg Sperl for helping with early research for this paper, Mickael Ly and Yi-Lu Chen for proofreading, and members of the ISTA Visual Computing Group for general feedback. This project was funded in part by the European Research Council (ERC Consolidator Grant 101045083 CoDiNA).\r\nThe motorboat and sailboat were modeled by Sergei and the palmtrees by YadroGames. The environment map was created by Emil Persson.","scopus_import":"1","isi":1,"department":[{"_id":"ChWo"}],"publisher":"Association for Computing Machinery","month":"08","file_date_updated":"2024-01-02T09:34:27Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"journal_article","volume":42,"ddc":["000"],"intvolume":"        42","doi":"10.1145/3592098","date_published":"2023-08-01T00:00:00Z","language":[{"iso":"eng"}],"tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","image":"/images/cc_by.png","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"status":"public","date_created":"2023-08-27T22:01:17Z","year":"2023","_id":"14240","acknowledged_ssus":[{"_id":"ScienComp"}],"quality_controlled":"1","oa_version":"Published Version","article_processing_charge":"Yes (in subscription journal)","article_type":"original","publication_status":"published","file":[{"creator":"sjeschke","access_level":"open_access","file_size":511572575,"content_type":"video/mp4","checksum":"1d178bb2f8011d9f5aedda6427e18c7a","date_updated":"2023-12-21T12:26:40Z","date_created":"2023-12-21T12:26:40Z","relation":"main_file","success":1,"file_id":"14704","file_name":"PaperVideo_final.mp4"},{"access_level":"open_access","creator":"dernst","checksum":"a49b2e744d5cd1276bb8b2e0ce6dc638","content_type":"application/pdf","file_size":7469177,"date_updated":"2024-01-02T09:34:27Z","file_name":"2023_ACMToG_Jeschke.pdf","file_id":"14725","date_created":"2024-01-02T09:34:27Z","success":1,"relation":"main_file"}],"abstract":[{"lang":"eng","text":"This paper introduces a novel method for simulating large bodies of water as a height field. At the start of each time step, we partition the waves into a bulk flow (which approximately satisfies the assumptions of the shallow water equations) and surface waves (which approximately satisfy the assumptions of Airy wave theory). We then solve the two wave regimes separately using appropriate state-of-the-art techniques, and re-combine the resulting wave velocities at the end of each step. This strategy leads to the first heightfield wave model capable of simulating complex interactions between both deep and shallow water effects, like the waves from a boat wake sloshing up onto a beach, or a dam break producing wave interference patterns and eddies. We also analyze the numerical dispersion created by our method and derive an exact correction factor for waves at a constant water depth, giving us a numerically perfect re-creation of theoretical water wave dispersion patterns."}],"day":"01","publication":"ACM Transactions on Graphics","publication_identifier":{"issn":["0730-0301"],"eissn":["1557-7368"]},"oa":1,"date_updated":"2024-01-02T09:35:55Z","citation":{"short":"S. Jeschke, C. Wojtan, ACM Transactions on Graphics 42 (2023).","ama":"Jeschke S, Wojtan C. Generalizing shallow water simulations with dispersive surface waves. <i>ACM Transactions on Graphics</i>. 2023;42(4). doi:<a href=\"https://doi.org/10.1145/3592098\">10.1145/3592098</a>","apa":"Jeschke, S., &#38; Wojtan, C. (2023). Generalizing shallow water simulations with dispersive surface waves. <i>ACM Transactions on Graphics</i>. Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3592098\">https://doi.org/10.1145/3592098</a>","ieee":"S. Jeschke and C. Wojtan, “Generalizing shallow water simulations with dispersive surface waves,” <i>ACM Transactions on Graphics</i>, vol. 42, no. 4. Association for Computing Machinery, 2023.","mla":"Jeschke, Stefan, and Chris Wojtan. “Generalizing Shallow Water Simulations with Dispersive Surface Waves.” <i>ACM Transactions on Graphics</i>, vol. 42, no. 4, 83, Association for Computing Machinery, 2023, doi:<a href=\"https://doi.org/10.1145/3592098\">10.1145/3592098</a>.","ista":"Jeschke S, Wojtan C. 2023. Generalizing shallow water simulations with dispersive surface waves. ACM Transactions on Graphics. 42(4), 83.","chicago":"Jeschke, Stefan, and Chris Wojtan. “Generalizing Shallow Water Simulations with Dispersive Surface Waves.” <i>ACM Transactions on Graphics</i>. Association for Computing Machinery, 2023. <a href=\"https://doi.org/10.1145/3592098\">https://doi.org/10.1145/3592098</a>."},"author":[{"last_name":"Jeschke","first_name":"Stefan","id":"44D6411A-F248-11E8-B48F-1D18A9856A87","full_name":"Jeschke, Stefan"},{"full_name":"Wojtan, Christopher J","id":"3C61F1D2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-6646-5546","last_name":"Wojtan","first_name":"Christopher J"}],"has_accepted_license":"1","issue":"4","article_number":"83","project":[{"name":"Computational Discovery of Numerical Algorithms for Animation and Simulation of Natural Phenomena","grant_number":"101045083","_id":"34bc2376-11ca-11ed-8bc3-9a3b3961a088"}],"external_id":{"isi":["001044671300049"]},"title":"Generalizing shallow water simulations with dispersive surface waves"},{"oa":1,"publication":"SIGGRAPH 2023 Conference Proceedings","publication_identifier":{"isbn":["9798400701597"]},"day":"23","author":[{"full_name":"Tojo, Kenji","first_name":"Kenji","last_name":"Tojo"},{"last_name":"Shamir","first_name":"Ariel","full_name":"Shamir, Ariel"},{"orcid":"0000-0001-6511-9385","id":"49876194-F248-11E8-B48F-1D18A9856A87","full_name":"Bickel, Bernd","first_name":"Bernd","last_name":"Bickel"},{"first_name":"Nobuyuki","last_name":"Umetani","full_name":"Umetani, Nobuyuki"}],"citation":{"short":"K. Tojo, A. Shamir, B. Bickel, N. Umetani, in:, SIGGRAPH 2023 Conference Proceedings, Association for Computing Machinery, 2023.","ista":"Tojo K, Shamir A, Bickel B, Umetani N. 2023. Stealth shaper: Reflectivity optimization as surface stylization. SIGGRAPH 2023 Conference Proceedings. SIGGRAPH: Computer Graphics and Interactive Techniques Conference, 20.","chicago":"Tojo, Kenji, Ariel Shamir, Bernd Bickel, and Nobuyuki Umetani. “Stealth Shaper: Reflectivity Optimization as Surface Stylization.” In <i>SIGGRAPH 2023 Conference Proceedings</i>. Association for Computing Machinery, 2023. <a href=\"https://doi.org/10.1145/3588432.3591542\">https://doi.org/10.1145/3588432.3591542</a>.","ieee":"K. Tojo, A. Shamir, B. Bickel, and N. Umetani, “Stealth shaper: Reflectivity optimization as surface stylization,” in <i>SIGGRAPH 2023 Conference Proceedings</i>, Los Angeles, CA, United States, 2023.","ama":"Tojo K, Shamir A, Bickel B, Umetani N. Stealth shaper: Reflectivity optimization as surface stylization. In: <i>SIGGRAPH 2023 Conference Proceedings</i>. Association for Computing Machinery; 2023. doi:<a href=\"https://doi.org/10.1145/3588432.3591542\">10.1145/3588432.3591542</a>","apa":"Tojo, K., Shamir, A., Bickel, B., &#38; Umetani, N. (2023). Stealth shaper: Reflectivity optimization as surface stylization. In <i>SIGGRAPH 2023 Conference Proceedings</i>. Los Angeles, CA, United States: Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3588432.3591542\">https://doi.org/10.1145/3588432.3591542</a>","mla":"Tojo, Kenji, et al. “Stealth Shaper: Reflectivity Optimization as Surface Stylization.” <i>SIGGRAPH 2023 Conference Proceedings</i>, 20, Association for Computing Machinery, 2023, doi:<a href=\"https://doi.org/10.1145/3588432.3591542\">10.1145/3588432.3591542</a>."},"date_updated":"2023-09-05T07:22:03Z","article_number":"20","title":"Stealth shaper: Reflectivity optimization as surface stylization","external_id":{"arxiv":["2305.05944"]},"_id":"14241","year":"2023","date_created":"2023-08-27T22:01:17Z","article_processing_charge":"No","oa_version":"Preprint","quality_controlled":"1","abstract":[{"lang":"eng","text":"We present a technique to optimize the reflectivity of a surface while preserving its overall shape. The naïve optimization of the mesh vertices using the gradients of reflectivity simulations results in undesirable distortion. In contrast, our robust formulation optimizes the surface normal as an independent variable that bridges the reflectivity term with differential rendering, and the regularization term with as-rigid-as-possible elastic energy. We further adaptively subdivide the input mesh to improve the convergence. Consequently, our method can minimize the retroreflectivity of a wide range of input shapes, resulting in sharply creased shapes ubiquitous among stealth aircraft and Sci-Fi vehicles. Furthermore, by changing the reward for the direction of the outgoing light directions, our method can be applied to other reflectivity design tasks, such as the optimization of architectural walls to concentrate light in a specific region. We have tested the proposed method using light-transport simulations and real-world 3D-printed objects."}],"publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"conference","status":"public","language":[{"iso":"eng"}],"date_published":"2023-07-23T00:00:00Z","doi":"10.1145/3588432.3591542","scopus_import":"1","acknowledgement":"The authors would like to thank Yuki Koyama and Takeo Igarashi for early discussions, and Yuta Yaguchi for support in 3D printing. This research is partially supported by the Israel Science Foundation grant number 1390/19.\r\n","conference":{"end_date":"2023-08-10","name":"SIGGRAPH: Computer Graphics and Interactive Techniques Conference","start_date":"2023-08-06","location":"Los Angeles, CA, United States"},"arxiv":1,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2305.05944","open_access":"1"}],"month":"07","publisher":"Association for Computing Machinery","department":[{"_id":"BeBi"}]},{"publication_status":"published","abstract":[{"lang":"eng","text":"We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore commonly adopted in industry. Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization, and certification of the quantized representation is necessary to guarantee robustness. In this work, we present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs. Inspired by advances in robust learning of non-quantized networks, our training algorithm computes the gradient of an abstract representation of the actual network. Unlike existing approaches, our method can handle the discrete semantics of QNNs. Based on QA-IBP, we also develop a complete verification procedure for verifying the adversarial robustness of QNNs, which is guaranteed to terminate and produce a correct answer. Compared to existing approaches, the key advantage of our verification procedure is that it runs entirely on GPU or other accelerator devices. We demonstrate experimentally that our approach significantly outperforms existing methods and establish the new state-of-the-art for training and certifying the robustness of QNNs."}],"quality_controlled":"1","oa_version":"Preprint","article_processing_charge":"No","ec_funded":1,"date_created":"2023-08-27T22:01:17Z","year":"2023","_id":"14242","project":[{"name":"Vigilant Algorithmic Monitoring of Software","grant_number":"101020093","call_identifier":"H2020","_id":"62781420-2b32-11ec-9570-8d9b63373d4d"},{"name":"Formal Methods for Stochastic Models: Algorithms and Applications","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","call_identifier":"H2020","grant_number":"863818"},{"_id":"2564DBCA-B435-11E9-9278-68D0E5697425","grant_number":"665385","call_identifier":"H2020","name":"International IST Doctoral Program"}],"external_id":{"arxiv":["2211.16187"]},"title":"Quantization-aware interval bound propagation for training certifiably robust quantized neural networks","issue":"12","citation":{"short":"M. Lechner, D. Zikelic, K. Chatterjee, T.A. Henzinger, D. Rus, in:, Proceedings of the 37th AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, 2023, pp. 14964–14973.","mla":"Lechner, Mathias, et al. “Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks.” <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, vol. 37, no. 12, Association for the Advancement of Artificial Intelligence, 2023, pp. 14964–73, doi:<a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">10.1609/aaai.v37i12.26747</a>.","ieee":"M. Lechner, D. Zikelic, K. Chatterjee, T. A. Henzinger, and D. Rus, “Quantization-aware interval bound propagation for training certifiably robust quantized neural networks,” in <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, Washington, DC, United States, 2023, vol. 37, no. 12, pp. 14964–14973.","apa":"Lechner, M., Zikelic, D., Chatterjee, K., Henzinger, T. A., &#38; Rus, D. (2023). Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i> (Vol. 37, pp. 14964–14973). Washington, DC, United States: Association for the Advancement of Artificial Intelligence. <a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">https://doi.org/10.1609/aaai.v37i12.26747</a>","ama":"Lechner M, Zikelic D, Chatterjee K, Henzinger TA, Rus D. Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. In: <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>. Vol 37. Association for the Advancement of Artificial Intelligence; 2023:14964-14973. doi:<a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">10.1609/aaai.v37i12.26747</a>","chicago":"Lechner, Mathias, Dorde Zikelic, Krishnendu Chatterjee, Thomas A Henzinger, and Daniela Rus. “Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks.” In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, 37:14964–73. Association for the Advancement of Artificial Intelligence, 2023. <a href=\"https://doi.org/10.1609/aaai.v37i12.26747\">https://doi.org/10.1609/aaai.v37i12.26747</a>.","ista":"Lechner M, Zikelic D, Chatterjee K, Henzinger TA, Rus D. 2023. Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. Proceedings of the 37th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 37, 14964–14973."},"date_updated":"2025-07-14T09:09:56Z","author":[{"last_name":"Lechner","first_name":"Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","full_name":"Lechner, Mathias"},{"full_name":"Zikelic, Dorde","id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-4681-1699","last_name":"Zikelic","first_name":"Dorde"},{"full_name":"Chatterjee, Krishnendu","id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-4561-241X","first_name":"Krishnendu","last_name":"Chatterjee"},{"full_name":"Henzinger, Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-2985-7724","last_name":"Henzinger","first_name":"Thomas A"},{"first_name":"Daniela","last_name":"Rus","full_name":"Rus, Daniela"}],"day":"26","publication":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","publication_identifier":{"isbn":["9781577358800"]},"oa":1,"publisher":"Association for the Advancement of Artificial Intelligence","department":[{"_id":"ToHe"},{"_id":"KrCh"}],"month":"06","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2211.16187"}],"arxiv":1,"page":"14964-14973","conference":{"location":"Washington, DC, United States","start_date":"2023-02-07","name":"AAAI: Conference on Artificial Intelligence","end_date":"2023-02-14"},"acknowledgement":"This work was supported in part by the ERC-2020-AdG 101020093, ERC CoG 863818 (FoRM-SMArt) and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 665385. Research was sponsored by the United\r\nStates Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator and was accomplished under Cooperative Agreement Number FA8750-19-2-\r\n1000. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied,\r\nof the United States Air Force or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright\r\nnotation herein. The research was also funded in part by the AI2050 program at Schmidt Futures (Grant G-22-63172) and Capgemini SE.","scopus_import":"1","doi":"10.1609/aaai.v37i12.26747","date_published":"2023-06-26T00:00:00Z","language":[{"iso":"eng"}],"status":"public","intvolume":"        37","type":"conference","volume":37,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87"},{"main_file_link":[{"url":"https://doi.org/10.1609/aaai.v37i5.25679","open_access":"1"}],"department":[{"_id":"ToHe"},{"_id":"KrCh"}],"month":"06","acknowledgement":"This research was supported in part by ISF grant no.1679/21, by the ERC CoG 863818 (ForM-SMArt), and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 665385.","scopus_import":"1","arxiv":1,"conference":{"end_date":"2023-02-14","location":"Washington, DC, United States","start_date":"2023-02-07","name":"AAAI: Conference on Artificial Intelligence"},"page":"5464-5471","intvolume":"        37","doi":"10.1609/aaai.v37i5.25679","date_published":"2023-06-27T00:00:00Z","language":[{"iso":"eng"}],"status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"conference","volume":37,"quality_controlled":"1","oa_version":"Published Version","article_processing_charge":"No","publication_status":"published","abstract":[{"lang":"eng","text":"Two-player zero-sum \"graph games\" are central in logic, verification, and multi-agent systems. The game proceeds by placing a token on a vertex of a graph, and allowing the players to move it to produce an infinite path, which determines the winner or payoff of the game. Traditionally, the players alternate turns in moving the token. In \"bidding games\", however, the players have budgets and in each turn, an auction (bidding) determines which player moves the token. So far, bidding games have only been studied as full-information games. In this work we initiate the study of partial-information bidding games: we study bidding games in which a player's initial budget is drawn from a known probability distribution. We show that while for some bidding mechanisms and objectives, it is straightforward to adapt the results from the full-information setting to the partial-information setting, for others, the analysis is significantly more challenging, requires new techniques, and gives rise to interesting results. Specifically, we study games with \"mean-payoff\" objectives in combination with \"poorman\" bidding. We construct optimal strategies for a partially-informed player who plays against a fully-informed adversary. We show that, somewhat surprisingly, the \"value\" under pure strategies does not necessarily exist in such games."}],"date_created":"2023-08-27T22:01:18Z","ec_funded":1,"year":"2023","_id":"14243","issue":"5","project":[{"name":"Formal Methods for Stochastic Models: Algorithms and Applications","_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","call_identifier":"H2020","grant_number":"863818"},{"name":"International IST Doctoral Program","_id":"2564DBCA-B435-11E9-9278-68D0E5697425","call_identifier":"H2020","grant_number":"665385"}],"external_id":{"arxiv":["2211.13626"]},"title":"Bidding graph games with partially-observable budgets","day":"27","publication_identifier":{"isbn":["9781577358800"]},"publication":"Proceedings of the 37th AAAI Conference on Artificial Intelligence","oa":1,"author":[{"first_name":"Guy","last_name":"Avni","id":"463C8BC2-F248-11E8-B48F-1D18A9856A87","full_name":"Avni, Guy","orcid":"0000-0001-5588-8287"},{"full_name":"Jecker, Ismael R","id":"85D7C63E-7D5D-11E9-9C0F-98C4E5697425","last_name":"Jecker","first_name":"Ismael R"},{"full_name":"Zikelic, Dorde","id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0002-4681-1699","last_name":"Zikelic","first_name":"Dorde"}],"citation":{"apa":"Avni, G., Jecker, I. R., &#38; Zikelic, D. (2023). Bidding graph games with partially-observable budgets. In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i> (Vol. 37, pp. 5464–5471). Washington, DC, United States. <a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">https://doi.org/10.1609/aaai.v37i5.25679</a>","ama":"Avni G, Jecker IR, Zikelic D. Bidding graph games with partially-observable budgets. In: <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>. Vol 37. ; 2023:5464-5471. doi:<a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">10.1609/aaai.v37i5.25679</a>","ieee":"G. Avni, I. R. Jecker, and D. Zikelic, “Bidding graph games with partially-observable budgets,” in <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, Washington, DC, United States, 2023, vol. 37, no. 5, pp. 5464–5471.","mla":"Avni, Guy, et al. “Bidding Graph Games with Partially-Observable Budgets.” <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, vol. 37, no. 5, 2023, pp. 5464–71, doi:<a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">10.1609/aaai.v37i5.25679</a>.","ista":"Avni G, Jecker IR, Zikelic D. 2023. Bidding graph games with partially-observable budgets. Proceedings of the 37th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 37, 5464–5471.","chicago":"Avni, Guy, Ismael R Jecker, and Dorde Zikelic. “Bidding Graph Games with Partially-Observable Budgets.” In <i>Proceedings of the 37th AAAI Conference on Artificial Intelligence</i>, 37:5464–71, 2023. <a href=\"https://doi.org/10.1609/aaai.v37i5.25679\">https://doi.org/10.1609/aaai.v37i5.25679</a>.","short":"G. Avni, I.R. Jecker, D. Zikelic, in:, Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023, pp. 5464–5471."},"date_updated":"2025-07-14T09:09:56Z"}]