---
_id: '14448'
abstract:
- lang: eng
  text: We consider the problem of solving LP relaxations of MAP-MRF inference problems,
    and in particular the method proposed recently in [16], [35]. As a key computational
    subroutine, it uses a variant of the Frank-Wolfe (FW) method to minimize a smooth
    convex function over a combinatorial polytope. We propose an efficient implementation
    of this subroutine based on in-face Frank-Wolfe directions, introduced in [4]
    in a different context. More generally, we define an abstract data structure for
    a combinatorial subproblem that enables in-face FW directions, and describe its
    specialization for tree-structured MAP-MRF inference subproblems. Experimental
    results indicate that the resulting method is the current state-of-art LP solver
    for some classes of problems. Our code is available at pub.ist.ac.at/~vnk/papers/IN-FACE-FW.html.
article_processing_charge: No
arxiv: 1
author:
- first_name: Vladimir
  full_name: Kolmogorov, Vladimir
  id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87
  last_name: Kolmogorov
citation:
  ama: 'Kolmogorov V. Solving relaxations of MAP-MRF problems: Combinatorial in-face
    Frank-Wolfe directions. In: <i>Proceedings of the IEEE Computer Society Conference
    on Computer Vision and Pattern Recognition</i>. Vol 2023. IEEE; 2023:11980-11989.
    doi:<a href="https://doi.org/10.1109/CVPR52729.2023.01153">10.1109/CVPR52729.2023.01153</a>'
  apa: 'Kolmogorov, V. (2023). Solving relaxations of MAP-MRF problems: Combinatorial
    in-face Frank-Wolfe directions. In <i>Proceedings of the IEEE Computer Society
    Conference on Computer Vision and Pattern Recognition</i> (Vol. 2023, pp. 11980–11989).
    Vancouver, Canada: IEEE. <a href="https://doi.org/10.1109/CVPR52729.2023.01153">https://doi.org/10.1109/CVPR52729.2023.01153</a>'
  chicago: 'Kolmogorov, Vladimir. “Solving Relaxations of MAP-MRF Problems: Combinatorial
    in-Face Frank-Wolfe Directions.” In <i>Proceedings of the IEEE Computer Society
    Conference on Computer Vision and Pattern Recognition</i>, 2023:11980–89. IEEE,
    2023. <a href="https://doi.org/10.1109/CVPR52729.2023.01153">https://doi.org/10.1109/CVPR52729.2023.01153</a>.'
  ieee: 'V. Kolmogorov, “Solving relaxations of MAP-MRF problems: Combinatorial in-face
    Frank-Wolfe directions,” in <i>Proceedings of the IEEE Computer Society Conference
    on Computer Vision and Pattern Recognition</i>, Vancouver, Canada, 2023, vol.
    2023, pp. 11980–11989.'
  ista: 'Kolmogorov V. 2023. Solving relaxations of MAP-MRF problems: Combinatorial
    in-face Frank-Wolfe directions. Proceedings of the IEEE Computer Society Conference
    on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision
    and Pattern Recognition vol. 2023, 11980–11989.'
  mla: 'Kolmogorov, Vladimir. “Solving Relaxations of MAP-MRF Problems: Combinatorial
    in-Face Frank-Wolfe Directions.” <i>Proceedings of the IEEE Computer Society Conference
    on Computer Vision and Pattern Recognition</i>, vol. 2023, IEEE, 2023, pp. 11980–89,
    doi:<a href="https://doi.org/10.1109/CVPR52729.2023.01153">10.1109/CVPR52729.2023.01153</a>.'
  short: V. Kolmogorov, in:, Proceedings of the IEEE Computer Society Conference on
    Computer Vision and Pattern Recognition, IEEE, 2023, pp. 11980–11989.
conference:
  end_date: 2023-06-24
  location: Vancouver, Canada
  name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
  start_date: 2023-06-17
date_created: 2023-10-22T22:01:16Z
date_published: 2023-08-22T00:00:00Z
date_updated: 2023-10-31T12:01:24Z
day: '22'
department:
- _id: VlKo
doi: 10.1109/CVPR52729.2023.01153
external_id:
  arxiv:
  - '2010.09567'
intvolume: '      2023'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: ' https://doi.org/10.48550/arXiv.2010.09567'
month: '08'
oa: 1
oa_version: Preprint
page: 11980-11989
publication: Proceedings of the IEEE Computer Society Conference on Computer Vision
  and Pattern Recognition
publication_identifier:
  isbn:
  - '9798350301298'
  issn:
  - 1063-6919
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Solving relaxations of MAP-MRF problems: Combinatorial in-face Frank-Wolfe
  directions'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 2023
year: '2023'
...
---
_id: '14114'
abstract:
- lang: eng
  text: Algorithmic fairness is frequently motivated in terms of a trade-off in which
    overall performance is decreased so as to improve performance on disadvantaged
    groups where the algorithm would otherwise be less accurate. Contrary to this,
    we find that applying existing fairness approaches to computer vision improve
    fairness by degrading the performance of classifiers across all groups (with increased
    degradation on the best performing groups). Extending the bias-variance decomposition
    for classification to fairness, we theoretically explain why the majority of fairness
    methods designed for low capacity models should not be used in settings involving
    high-capacity models, a scenario common to computer vision. We corroborate this
    analysis with extensive experimental support that shows that many of the fairness
    heuristics used in computer vision also degrade performance on the most disadvantaged
    groups. Building on these insights, we propose an adaptive augmentation strategy
    that, uniquely, of all methods tested, improves performance for the disadvantaged
    groups.
article_processing_charge: No
arxiv: 1
author:
- first_name: Dominik
  full_name: Zietlow, Dominik
  last_name: Zietlow
- first_name: Michael
  full_name: Lohaus, Michael
  last_name: Lohaus
- first_name: Guha
  full_name: Balakrishnan, Guha
  last_name: Balakrishnan
- first_name: Matthaus
  full_name: Kleindessner, Matthaus
  last_name: Kleindessner
- first_name: Francesco
  full_name: Locatello, Francesco
  id: 26cfd52f-2483-11ee-8040-88983bcc06d4
  last_name: Locatello
  orcid: 0000-0002-4850-0683
- first_name: Bernhard
  full_name: Scholkopf, Bernhard
  last_name: Scholkopf
- first_name: Chris
  full_name: Russell, Chris
  last_name: Russell
citation:
  ama: 'Zietlow D, Lohaus M, Balakrishnan G, et al. Leveling down in computer vision:
    Pareto inefficiencies in fair deep classifiers. In: <i>2022 IEEE/CVF Conference
    on Computer Vision and Pattern Recognition</i>. Institute of Electrical and Electronics
    Engineers; 2022:10400-10411. doi:<a href="https://doi.org/10.1109/cvpr52688.2022.01016">10.1109/cvpr52688.2022.01016</a>'
  apa: 'Zietlow, D., Lohaus, M., Balakrishnan, G., Kleindessner, M., Locatello, F.,
    Scholkopf, B., &#38; Russell, C. (2022). Leveling down in computer vision: Pareto
    inefficiencies in fair deep classifiers. In <i>2022 IEEE/CVF Conference on Computer
    Vision and Pattern Recognition</i> (pp. 10400–10411). New Orleans, LA, United
    States: Institute of Electrical and Electronics Engineers. <a href="https://doi.org/10.1109/cvpr52688.2022.01016">https://doi.org/10.1109/cvpr52688.2022.01016</a>'
  chicago: 'Zietlow, Dominik, Michael Lohaus, Guha Balakrishnan, Matthaus Kleindessner,
    Francesco Locatello, Bernhard Scholkopf, and Chris Russell. “Leveling down in
    Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers.” In <i>2022 IEEE/CVF
    Conference on Computer Vision and Pattern Recognition</i>, 10400–411. Institute
    of Electrical and Electronics Engineers, 2022. <a href="https://doi.org/10.1109/cvpr52688.2022.01016">https://doi.org/10.1109/cvpr52688.2022.01016</a>.'
  ieee: 'D. Zietlow <i>et al.</i>, “Leveling down in computer vision: Pareto inefficiencies
    in fair deep classifiers,” in <i>2022 IEEE/CVF Conference on Computer Vision and
    Pattern Recognition</i>, New Orleans, LA, United States, 2022, pp. 10400–10411.'
  ista: 'Zietlow D, Lohaus M, Balakrishnan G, Kleindessner M, Locatello F, Scholkopf
    B, Russell C. 2022. Leveling down in computer vision: Pareto inefficiencies in
    fair deep classifiers. 2022 IEEE/CVF Conference on Computer Vision and Pattern
    Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 10400–10411.'
  mla: 'Zietlow, Dominik, et al. “Leveling down in Computer Vision: Pareto Inefficiencies
    in Fair Deep Classifiers.” <i>2022 IEEE/CVF Conference on Computer Vision and
    Pattern Recognition</i>, Institute of Electrical and Electronics Engineers, 2022,
    pp. 10400–11, doi:<a href="https://doi.org/10.1109/cvpr52688.2022.01016">10.1109/cvpr52688.2022.01016</a>.'
  short: D. Zietlow, M. Lohaus, G. Balakrishnan, M. Kleindessner, F. Locatello, B.
    Scholkopf, C. Russell, in:, 2022 IEEE/CVF Conference on Computer Vision and Pattern
    Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 10400–10411.
conference:
  end_date: 2022-06-24
  location: New Orleans, LA, United States
  name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
  start_date: 2022-06-18
date_created: 2023-08-21T12:18:00Z
date_published: 2022-07-01T00:00:00Z
date_updated: 2023-09-11T09:19:14Z
day: '01'
department:
- _id: FrLo
doi: 10.1109/cvpr52688.2022.01016
extern: '1'
external_id:
  arxiv:
  - '2203.04913'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://arxiv.org/abs/2203.04913
month: '07'
oa: 1
oa_version: Preprint
page: 10400-10411
publication: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
  eissn:
  - 2575-7075
  isbn:
  - '9781665469470'
  issn:
  - 1063-6919
publication_status: published
publisher: Institute of Electrical and Electronics Engineers
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2022'
...
---
_id: '9957'
abstract:
- lang: eng
  text: The reflectance field of a face describes the reflectance properties responsible
    for complex lighting effects including diffuse, specular, inter-reflection and
    self shadowing. Most existing methods for estimating the face reflectance from
    a monocular image assume faces to be diffuse with very few approaches adding a
    specular component. This still leaves out important perceptual aspects of reflectance
    as higher-order global illumination effects and self-shadowing are not modeled.
    We present a new neural representation for face reflectance where we can estimate
    all components of the reflectance responsible for the final appearance from a
    single monocular image. Instead of modeling each component of the reflectance
    separately using parametric models, our neural representation allows us to generate
    a basis set of faces in a geometric deformation-invariant space, parameterized
    by the input light direction, viewpoint and face geometry. We learn to reconstruct
    this reflectance field of a face just from a monocular image, which can be used
    to render the face from any viewpoint in any light condition. Our method is trained
    on a light-stage training dataset, which captures 300 people illuminated with
    150 light conditions from 8 viewpoints. We show that our method outperforms existing
    monocular reflectance reconstruction methods, in terms of photorealism due to
    better capturing of physical premitives, such as sub-surface scattering, specularities,
    self-shadows and other higher-order effects.
acknowledgement: "We thank Tarun Yenamandra and Duarte David for helping us with the
  comparisons. This work was supported by the\r\nERC Consolidator Grant 4DReply (770784).
  We also acknowledge support from InterDigital."
article_processing_charge: No
arxiv: 1
author:
- first_name: Mallikarjun
  full_name: B R, Mallikarjun
  last_name: B R
- first_name: Ayush
  full_name: Tewari, Ayush
  last_name: Tewari
- first_name: Tae-Hyun
  full_name: Oh, Tae-Hyun
  last_name: Oh
- first_name: Tim
  full_name: Weyrich, Tim
  last_name: Weyrich
- first_name: Bernd
  full_name: Bickel, Bernd
  id: 49876194-F248-11E8-B48F-1D18A9856A87
  last_name: Bickel
  orcid: 0000-0001-6511-9385
- first_name: Hans-Peter
  full_name: Seidel, Hans-Peter
  last_name: Seidel
- first_name: Hanspeter
  full_name: Pfister, Hanspeter
  last_name: Pfister
- first_name: Wojciech
  full_name: Matusik, Wojciech
  last_name: Matusik
- first_name: Mohamed
  full_name: Elgharib, Mohamed
  last_name: Elgharib
- first_name: Christian
  full_name: Theobalt, Christian
  last_name: Theobalt
citation:
  ama: 'B R M, Tewari A, Oh T-H, et al. Monocular reconstruction of neural face reflectance
    fields. In: <i>Proceedings of the IEEE Computer Society Conference on Computer
    Vision and Pattern Recognition</i>. IEEE; 2021:4791-4800. doi:<a href="https://doi.org/10.1109/CVPR46437.2021.00476">10.1109/CVPR46437.2021.00476</a>'
  apa: 'B R, M., Tewari, A., Oh, T.-H., Weyrich, T., Bickel, B., Seidel, H.-P., …
    Theobalt, C. (2021). Monocular reconstruction of neural face reflectance fields.
    In <i>Proceedings of the IEEE Computer Society Conference on Computer Vision and
    Pattern Recognition</i> (pp. 4791–4800). Nashville, TN, United States; Virtual:
    IEEE. <a href="https://doi.org/10.1109/CVPR46437.2021.00476">https://doi.org/10.1109/CVPR46437.2021.00476</a>'
  chicago: B R, Mallikarjun, Ayush Tewari, Tae-Hyun Oh, Tim Weyrich, Bernd Bickel,
    Hans-Peter Seidel, Hanspeter Pfister, Wojciech Matusik, Mohamed Elgharib, and
    Christian Theobalt. “Monocular Reconstruction of Neural Face Reflectance Fields.”
    In <i>Proceedings of the IEEE Computer Society Conference on Computer Vision and
    Pattern Recognition</i>, 4791–4800. IEEE, 2021. <a href="https://doi.org/10.1109/CVPR46437.2021.00476">https://doi.org/10.1109/CVPR46437.2021.00476</a>.
  ieee: M. B R <i>et al.</i>, “Monocular reconstruction of neural face reflectance
    fields,” in <i>Proceedings of the IEEE Computer Society Conference on Computer
    Vision and Pattern Recognition</i>, Nashville, TN, United States; Virtual, 2021,
    pp. 4791–4800.
  ista: 'B R M, Tewari A, Oh T-H, Weyrich T, Bickel B, Seidel H-P, Pfister H, Matusik
    W, Elgharib M, Theobalt C. 2021. Monocular reconstruction of neural face reflectance
    fields. Proceedings of the IEEE Computer Society Conference on Computer Vision
    and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition,
    4791–4800.'
  mla: B R, Mallikarjun, et al. “Monocular Reconstruction of Neural Face Reflectance
    Fields.” <i>Proceedings of the IEEE Computer Society Conference on Computer Vision
    and Pattern Recognition</i>, IEEE, 2021, pp. 4791–800, doi:<a href="https://doi.org/10.1109/CVPR46437.2021.00476">10.1109/CVPR46437.2021.00476</a>.
  short: M. B R, A. Tewari, T.-H. Oh, T. Weyrich, B. Bickel, H.-P. Seidel, H. Pfister,
    W. Matusik, M. Elgharib, C. Theobalt, in:, Proceedings of the IEEE Computer Society
    Conference on Computer Vision and Pattern Recognition, IEEE, 2021, pp. 4791–4800.
conference:
  end_date: 2021-06-25
  location: Nashville, TN, United States; Virtual
  name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
  start_date: 2021-06-20
date_created: 2021-08-24T06:03:00Z
date_published: 2021-09-01T00:00:00Z
date_updated: 2023-08-11T11:08:35Z
day: '01'
ddc:
- '000'
department:
- _id: BeBi
doi: 10.1109/CVPR46437.2021.00476
external_id:
  arxiv:
  - '2008.10247'
  isi:
  - '000739917304096'
file:
- access_level: open_access
  checksum: 961db0bde76dd87cf833930080bb9f38
  content_type: application/pdf
  creator: bbickel
  date_created: 2021-08-24T06:02:15Z
  date_updated: 2021-08-24T06:02:15Z
  file_id: '9958'
  file_name: R_Monocular_Reconstruction_of_Neural_Face_Reflectance_Fields_CVPR_2021_paper[1].pdf
  file_size: 4746649
  relation: main_file
file_date_updated: 2021-08-24T06:02:15Z
has_accepted_license: '1'
isi: 1
language:
- iso: eng
month: '09'
oa: 1
oa_version: Preprint
page: 4791-4800
publication: Proceedings of the IEEE Computer Society Conference on Computer Vision
  and Pattern Recognition
publication_identifier:
  isbn:
  - 978-166544509-2
  issn:
  - 1063-6919
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Monocular reconstruction of neural face reflectance fields
type: conference
user_id: 4359f0d1-fa6c-11eb-b949-802e58b17ae8
year: '2021'
...