ASIF: Coupled data turns unimodal models to multimodal without training

Norelli A, Fumero M, Maiorca V, Moschella L, Rodolà E, Locatello F. ASIF: Coupled data turns unimodal models to multimodal without training. arXiv, 2210.01738.

Download (ext.)

Preprint | Submitted | English
Author
Norelli, Antonio; Fumero, Marco; Maiorca, Valentino; Moschella, Luca; Rodolà, Emanuele; Locatello, FrancescoISTA
Department
Abstract
CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to train image and text encoders from scratch on a huge dataset. LiT improved this by only training the text encoder and using a pre-trained vision network. In this paper, we show that a common space can be created without any training at all, using single-domain encoders (trained with or without supervision) and a much smaller amount of image-text pairs. Furthermore, our model has unique properties. Most notably, deploying a new version with updated training samples can be done in a matter of seconds. Additionally, the representations in the common space are easily interpretable as every dimension corresponds to the similarity of the input to a unique entry in the multimodal dataset. Experiments on standard zero-shot visual benchmarks demonstrate the typical transfer ability of image-text models. Overall, our method represents a simple yet surprisingly strong baseline for foundation multi-modal models, raising important questions on their data efficiency and on the role of retrieval in machine learning.
Publishing Year
Date Published
2022-10-04
Journal Title
arXiv
Article Number
2210.01738
IST-REx-ID

Cite this

Norelli A, Fumero M, Maiorca V, Moschella L, Rodolà E, Locatello F. ASIF: Coupled data turns unimodal models to multimodal without training. arXiv. doi:10.48550/arXiv.2210.01738
Norelli, A., Fumero, M., Maiorca, V., Moschella, L., Rodolà, E., & Locatello, F. (n.d.). ASIF: Coupled data turns unimodal models to multimodal without training. arXiv. https://doi.org/10.48550/arXiv.2210.01738
Norelli, Antonio, Marco Fumero, Valentino Maiorca, Luca Moschella, Emanuele Rodolà, and Francesco Locatello. “ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2210.01738.
A. Norelli, M. Fumero, V. Maiorca, L. Moschella, E. Rodolà, and F. Locatello, “ASIF: Coupled data turns unimodal models to multimodal without training,” arXiv. .
Norelli A, Fumero M, Maiorca V, Moschella L, Rodolà E, Locatello F. ASIF: Coupled data turns unimodal models to multimodal without training. arXiv, 2210.01738.
Norelli, Antonio, et al. “ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training.” ArXiv, 2210.01738, doi:10.48550/arXiv.2210.01738.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 2210.01738

Search this title in

Google Scholar