CoChat
Sign Up
Cited by 141Emotion and Mood RecognitionFace recognition and analysisDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Face2Exp: Combating Data Biases for Facial Expression Recognition

Zeng, Dan, Lin, Zhiyuan, Yan, Xiao, Liu, Yuting, Wang, Fei, Tang, Bo·2022·2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr52688.2022.01965
Open this paper in CoChat — free account

Abstract

Facial expression recognition (FER) is challenging due to the class imbalance caused by data collection. Existing studies tackle the data bias problem using only labeled facial expression dataset. Orthogonal to existing FER methods, we propose to utilize large unlabeled face recognition (FR) datasets to enhance FER. However, this raises another data bias problem—the distribution mismatch between FR and FER data. To combat the mismatch, we propose the Meta-Face2Exp framework, which consists of a base network and an adaptation network. The base network learns prior expression knowledge on class-balanced FER data while the adaptation network is trained to fit the pseudo labels of FR data generated by the base model. To combat the mismatch between FR and FER data, Meta-Face2Exp uses a circuit feedback mechanism, which improves the base network with the feedback from the adaptation network. Experiments show that our MetaFace2Exp achieves comparable accuracy to state-of-the-art FER methods with 10% of the labeled FER data utilized by the baselines. We also demonstrate that the circuit feedback mechanism successfully eliminates data bias11Code is available at link: https://github.com/danzeng1990/Face2Exp..

Overview

Integrity signals

Registry

Crossref · 10.1109/cvpr52688.2022.01965

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • FER training datasets have bias in their class distribution.

    “Zeng et al. [28] showed the bias in the class distribution of FER training datasets.”

    From SAFER: Situation Aware Facial Emotion Recognition (2023) · cites this paper as [28]

  • Recent works have proposed algorithmic methods to deal with bias in datasets.

    “Recent works have proposed several algorithmic methods to deal with the above-mentioned bias in the datasets [28, 19, 44].”

    From SAFER: Situation Aware Facial Emotion Recognition (2023) · cites this paper as [28]

  • These methods do not mitigate the problem completely.

    “However, these methods do not mitigate the problem completely.”

    From SAFER: Situation Aware Facial Emotion Recognition (2023) · cites this paper as [28]

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 39

  1. 10.29007/qwpk · DOI
  2. 10.1109/ACCESS.2019.2930359 · DOI
  3. xie, 2019, Unsupervised data augmentation for consistency training, ArXiv Preprint
  4. 10.1016/j.patcog.2020.107694 · DOI
  5. 10.1155/2018/7208794 · DOI
  6. 10.1109/TIP.2019.2956143 · DOI
  7. 10.1016/j.neucom.2015.11.113 · DOI
  8. 10.1109/ICCV48922.2021.00358 · DOI
  9. 10.1145/3394171.3413822 · DOI
  10. 10.1109/CVPR42600.2020.01070 · DOI · Paper page
  11. 10.1109/WACV48630.2021.00245 · DOI
  12. zeng, 0, Facial expression recognition with inconsistently annotated datasets, Proceedings of the European Conference on Computer Vision (ECCV), 222
  13. florea, 0, Margin-mix: Semi-supervised learning for face expression recognition, Proceedings of the European Conference on Computer Vision (ECCV), 1
  14. florea, 0, Annealed label transfer for face expression recognition, BMVC, 104
  15. guo, 0, Ms-celeb-1m: A dataset and benchmark for large-scale face recognition, Proceedings of the European Conference on Computer Vision (ECCV), 87
  16. 10.1007/s10462-021-10004-4 · DOI
  17. kervadec, 2018, Cake: Compact and accurate k-dimensional representation of emotion, ArXiv Preprint
  18. lee, 0, Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks, Workshop on Challenges in Representation Learning, 3, 896
  19. li, 2020, A deeper look at facial expression dataset bias, IEEE Transactions on Affective Computing
  20. 10.1109/CVPR.2017.277 · DOI · Paper page
  21. wang, 2020, Au-guided unsupervised domain adaptive facial expression recognition, ArXiv Preprint
  22. 10.1016/j.patcog.2021.107893 · DOI
  23. sohn, 2020, Fixmatch: Simplifying semi-supervised learning with consistency and confidence, ArXiv Preprint
  24. 10.1109/TPAMI.2004.127 · DOI
  25. 10.1109/CVPR42600.2020.01400 · DOI
  26. 10.1109/CVPRW50498.2020.00359 · DOI · Paper page
  27. cohn, 2015, Automated Face Analysis for Affective Computing
  28. 10.1109/CVPRW.2003.10057 · DOI
  29. 10.1109/FG.2017.23 · DOI · Paper page
  30. 10.1109/EMS.2011.20 · DOI
  31. 10.1109/TIP.2018.2886767 · DOI · Paper page
  32. 10.1109/TAFFC.2017.2740923 · DOI · Paper page
  33. 10.1007/978-3-642-37444-9_45 · DOI
  34. 10.1109/CVPR46437.2021.01035 · DOI
  35. 10.1007/978-3-642-33783-3_58 · DOI · Paper page
  36. 10.1109/LSP.2016.2603342 · DOI · Paper page
  37. 10.1109/CVPR46437.2021.01139 · DOI
  38. 10.1109/CVPR46437.2021.00618 · DOI
  39. 10.1109/CVPR46437.2021.00757 · DOI

Cited by

Sorted by citations

Metadata

Authors
Zeng, D., Lin, Z., Yan, X., Liu, Y., Wang, F., & Tang, B.
Affiliations
  • Southern University of Science and Technology (CN)
  • Research Institue of Trustworthy Autonomous Systems, Southern University of Science and Technology, Southern University of Science and Technology,Department of Computer Science and Engineering
  • Jingdong (China) (CN)
ORCID
Venue
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2022-06
Pages
20259-20268
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr52688.2022.01965
OpenAlex
W4312823769
Cited by
141
References
3
Citations by year
2026: 25 · 2025: 38 · 2024: 53 · 2023: 24 · 2022: 1
FWCI
37.93
Type
conference paper
Language
en
Open access
closed
Licence
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
Funders
National Natural Science Foundation of China (62176170,62066042)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
facial expression recognition, data bias, class imbalance, distribution mismatch, pseudo-labeling, domain adaptation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review