Progressive Masking Oriented Self-Taught Learning for Occluded Facial Expression Recognition

Self-taught learning (STL) is a promising solution that reduces the performance gap between weakly supervised and fully supervised learning for easily accessible, label-free images. The success of traditional STL solutions relies on the assumption that the target appearance is completely visible and well-defined. In real-world facial expression recognition scenarios, however, saliency regions are often partially occluded, which significantly hampers the generalization capability of STL methods. Nevertheless, few studies have investigated the impact of occlusion on STL. In this paper, we propose an interweaved autoencoder network for weakly supervised facial expression recognition in occlusion scenarios. The key innovation of our network lies in the Residual Connection Union (RCU) blocks that can integrate the Convolutional Neural Network (CNN) and Transformer layers into a multi-scale structure. The RCU enables a progressive masking strategy to accurately identify and focus on contributive yet often overlooked image patches by analyzing the relationships among region-level target representations. In addition, we introduce a self-knowledge distillation module for the effective training of the proposed autoencoder network. Extensive experiments are conducted on four public datasets to demonstrate the superiority of our method over related works.