Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training
Not on the map. Why?
Abstract (arXiv)
Facial expression recognition (FER) in the wild is crucial for building reliable human-computer interactive systems. However, annotations of large scale datasets in FER has been a key challenge as these datasets suffer from noise due to various factors like crowd sourcing, subjectivity of annotators, poor quality of images, automatic labelling based on key word search etc. Such noisy annotations impede the performance of FER due to the memorization ability of deep networks. 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 report presents Consensual Collaborative Training (CCT) framework used in our submission to expression recognition track of the Affective Behaviour Analysis in-the-wild (ABAW) 2021 competition. 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. Co-training reduces overall error, and consistency loss prevents overfitting to noisy samples. The performance of the model is validated on challenging Aff-Wild2 dataset for categorical expression classification. Our code is made publicly available at https://github.com/1980x/ABAW2021DMACS.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 46 of its 91 references that are in the map. First posted on arXiv 8 Jul 2021.
Builds on
46 of 91 references.
References · 46
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2016Understanding deep learning requires rethinking generalizationcited by 1,657
- 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
- 2017A Closer Look at Memorization in Deep Networkscited by 936
- 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
- 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
- 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
- 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
- 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
- 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
34 more
- 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 490
- 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
- 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
- 2018Deep Facial Expression Recognition: A Surveycited by 269
- 2017Decoupling "when to update" from "how to update"cited by 230
- 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
- 2018Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcited by 216
- 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
- 2020Analysing Affective Behavior in the First ABAW 2020 Competitioncited by 178
- 2021Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Frameworkcited by 174
- 2021Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Studycited by 168
- 2021Analysing Affective Behavior in the second ABAW2 Competitioncited by 163
- 2016Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distributioncited by 158
- 2020Suppressing Uncertainties for Large-Scale Facial Expression Recognitioncited by 157
- 2019Face Behavior a la carte: Expressions, Affect and Action Units in a Single Networkcited by 155
- 2019NLNL: Negative Learning for Noisy Labelscited by 151
- 2019Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognitioncited by 127
- 2018Aff-Wild2: Extending the Aff-Wild Database for Affect Recognitioncited by 80
- 2018A Compact Embedding for Facial Expression Similaritycited by 41
- 2018Covariance Pooling For Facial Expression Recognitioncited by 37
- 2019IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matterscited by 33
- 2018A Multi-Task Learning & Generation Framework: Valence-Arousal, Action Units & Primary Expressionscited by 25
- 2020Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networkscited by 24
- 2018Local Learning with Deep and Handcrafted Features for Facial Expression Recognitioncited by 23
- 2019Facial Motion Prior Networks for Facial Expression Recognitioncited by 20
- 2020Occlusion-Adaptive Deep Network for Robust Facial Expression Recognitioncited by 17
- 2020Noisy Concurrent Training for Efficient Learning under Label Noisecited by 13
- 2021An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wildcited by 12
- 2020THIN: THrowable Information Networks and Application for Facial Expression Recognition In The Wildcited by 9
- 2017Coupled Ensembles of Neural Networkscited by 8
- 2020Kernelized dense layers for facial expression recognitioncited by 7
- 2020Semantic Neighborhood-Aware Deep Facial Expression Recognitioncited by 5
- 2021Multi-modal Affect Analysis using standardized data within subjects in the Wildcited by 4
- 2018Deep Neural Network Augmentation: Generating Faces for Affect Analysiscited by 2
Built on by
Citing papers per year: 2021: 1; 2022: 1.
2 papers.