Robust Lightweight Facial Expression Recognition Network with Label Distribution Training

Authors

  • Zengqun Zhao Nanjing University of Information Science & Technology, Nanjing, China
  • Qingshan Liu Nanjing University of Information Science & Technology, Nanjing, China
  • Feng Zhou Nanjing University of Information Science & Technology, Nanjing, China

Keywords:

Biometrics, Face, Gesture & Pose

Abstract

This paper presents an efficiently robust facial expression recognition (FER) network, named EfficientFace, which holds much fewer parameters but more robust to the FER in the wild. Firstly, to improve the robustness of the lightweight network, a local-feature extractor and a channel-spatial modulator are designed, in which the depthwise convolution is employed. As a result, the network is aware of local and global-salient facial features. Then, considering the fact that most emotions occur as combinations, mixtures, or compounds of the basic emotions, we introduce a simple but efficient label distribution learning (LDL) method as a novel training strategy. Experiments conducted on realistic occlusion and pose variation datasets demonstrate that the proposed EfficientFace is robust under occlusion and pose variation conditions. Moreover, the proposed method achieves state-of-the-art results on RAF-DB, CAER-S, and AffectNet-7 datasets with accuracies of 88.36%, 85.87%, and 63.70%, respectively, and a comparable result on the AffectNet-8 dataset with an accuracy of 59.89%. The code is public available at https://github.com/zengqunzhao/EfficientFace.

Downloads

Published

2021-05-18

How to Cite

Zhao, Z., Liu, Q., & Zhou, F. (2021). Robust Lightweight Facial Expression Recognition Network with Label Distribution Training. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3510-3519. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16465

Issue

Section

AAAI Technical Track on Computer Vision III