mlsanityData to 7 Oct 2026

Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations

arXiv 2107.04746 ↗First posted 10 Jul 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Presence of noise in the labels of large scale facial expression datasets has been a key challenge towards Facial Expression Recognition (FER) in the wild. During early learning stage, deep networks fit on clean data. Then, eventually, they start overfitting on noisy labels due to their memorization ability, which limits FER performance. This work proposes an effective training strategy in the presence of noisy labels, called as Consensual Collaborative Training (CCT) framework. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss, without making any assumption about the noise distribution. A dynamic transition mechanism is used to move from supervision loss in early learning to consistency loss for consensus of predictions among networks in the later stage. Inference is done using a single network based on a simple knowledge distillation scheme. Effectiveness of the proposed framework is demonstrated on synthetic as well as real noisy FER datasets. In addition, a large test subset of around 5K images is annotated from the FEC dataset using crowd wisdom of 16 different annotators and reliable labels are inferred. CCT is also validated on it. State-of-the-art performance is reported on the benchmark FER datasets RAFDB (90.84%) FERPlus (89.99%) and AffectNet (66%). Our codes are available at https://github.com/1980x/CCT.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 91 references that are in the map. First posted on arXiv 10 Jul 2021.

Builds on

52 of 91 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  6. 2017A Closer Look at Memorization in Deep Networkscited by 936
  7. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  8. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  9. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  10. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  11. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  12. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
38 more
  1. 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 490
  2. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  3. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  4. 2018Deep Facial Expression Recognition: A Surveycited by 269
  5. 2017Decoupling "when to update" from "how to update"cited by 230
  6. 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
  7. 2018Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcited by 216
  8. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  9. 2020Analysing Affective Behavior in the First ABAW 2020 Competitioncited by 178
  10. 2021Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Frameworkcited by 174
  11. 2021Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Studycited by 168
  12. 2021Analysing Affective Behavior in the second ABAW2 Competitioncited by 163
  13. 2016Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distributioncited by 158
  14. 2020Suppressing Uncertainties for Large-Scale Facial Expression Recognitioncited by 157
  15. 2019Face Behavior a la carte: Expressions, Affect and Action Units in a Single Networkcited by 155
  16. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  17. 2019Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognitioncited by 127
  18. 2018Aff-Wild2: Extending the Aff-Wild Database for Affect Recognitioncited by 80
  19. 2018A Compact Embedding for Facial Expression Similaritycited by 41
  20. 2018Covariance Pooling For Facial Expression Recognitioncited by 37
  21. 2019IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matterscited by 33
  22. 2018A Multi-Task Learning & Generation Framework: Valence-Arousal, Action Units & Primary Expressionscited by 25
  23. 2020Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networkscited by 24
  24. 2021A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognitioncited by 24
  25. 2018Local Learning with Deep and Handcrafted Features for Facial Expression Recognitioncited by 23
  26. 2019Facial Motion Prior Networks for Facial Expression Recognitioncited by 20
  27. 2021A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysiscited by 19
  28. 2021Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competitioncited by 18
  29. 2020Occlusion-Adaptive Deep Network for Robust Facial Expression Recognitioncited by 17
  30. 2020Noisy Concurrent Training for Efficient Learning under Label Noisecited by 13
  31. 2021An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wildcited by 12
  32. 2021Multitask Multi-database Emotion Recognitioncited by 12
  33. 2021Emotion Recognition with Incomplete Labels Using Modified Multi-task Learning Techniquecited by 10
  34. 2020THIN: THrowable Information Networks and Application for Facial Expression Recognition In The Wildcited by 9
  35. 2017Coupled Ensembles of Neural Networkscited by 8
  36. 2020Kernelized dense layers for facial expression recognitioncited by 7
  37. 2020Semantic Neighborhood-Aware Deep Facial Expression Recognitioncited by 5
  38. 2021Multi-modal Affect Analysis using standardized data within subjects in the Wildcited by 4

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.