Facial Emotion Recognition with Noisy Multi-task Annotations

Abstract

Human emotions can be inferred from facial expressions. However, the annotations of facial expressions are often highly noisy in common emotion coding models, including categorical and dimensional ones. To reduce human labelling effort on multi-task labels, we introduce a new problem of facial emotion recognition with noisy multi-task annotations. For this new problem, we suggest a formulation from the point of joint distribution match view, which aims at learning more reliable correlations among raw facial images and multi-task labels, resulting in the reduction of noise influence. In our formulation, we exploit a new method to enable the emotion prediction and the joint distribution learning in a unified adversarial learning game. Evaluation throughout extensive experiments studies the real setups of the suggested new problem, as well as the clear superiority of the proposed method over the state-of-the-art competing methods on either the synthetic noisy labeled CIFAR-10 or practical noisy multi-task labeled RAF and AffectNet. The code is available at https://github.com/sanweiliti/noisyFER.

arXiv commentAccepted by 2021 WACV, camera-ready version with appendix

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
• Adversarial Feature Learning
• Adversarially Learned Inference
• Deep Label Distribution Learning with Label Ambiguity
• MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
• Training Convolutional Networks with Noisy Labels
• Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond
• Dimensionality-Driven Learning with Noisy Labels
• Triple Generative Adversarial Nets
• How does Disagreement Help Generalization against Label Corruption?
• Aff-Wild2: Extending the Aff-Wild Database for Affect Recognition
• Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace
• Multi-task, multi-label and multi-domain learning with residual convolutional networks for emotion recognition
• JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
• Auxiliary Image Regularization for Deep CNNs with Noisy Labels