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.
QUB-PHEO: A Visual-Based Dyadic Multi-View Dataset for Intention Inference in Collaborative Assembly
Centre for Intelligent Autonomous Manufacturing Systems, Queen’s University Belfast（智能自主制造系统研究中心，女王大学贝尔法斯特）；School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast（电子、电气工程与计算机科学学院，女王大学贝尔法斯特）；School of Psychology, Queen’s University Belfast（心理学学院，女王大学贝尔法斯特）
ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset
School of Basic Medical Sciences, Guangzhou Medical University（广州医科大学基础医学院）；University of South Carolina（南卡罗来纳大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）
MEDN: Motion-Emotion Feature Decoupling Network for Micro-Expression Recognition
School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院）；Xi’an Key Laboratory of Big Data and Intelligent Vision, Xi’an, Shaanxi（西安大数据与智能视觉重点实验室）；Key Laboratory of Collaborative Intelligence Systems, Ministry of Education, Xidian University（教育部协同智能系统重点实验室）；National Engineering Research Center of Educational Big Data and the Faculty of Artificial Intelligence in Education, Central China Normal University（教育大数据国家工程研究中心和华中师范大学人工智能教育学院）
