会议论文

Xie, W

英文

2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME

1945-7871

2023

234-239

IEEE International Conference on Multimedia and Expo (ICME)

IEEE International Conference on Multimedia and Expo

JUL 10-14, 2023

Brisbane, AUSTRALIA

[Sun, Hao;Pi, Chenchen;Xie, Wei] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan, Peoples R China.^[Sun, Hao;Pi, Chenchen;Xie, Wei] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.^[Sun, Hao;Pi, Chenchen;Xie, Wei] Cent China Normal Univ, Natl Language Resources Monitoring & Res Ctr Netw, Wuhan, Peoples R China.

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

978-1-6654-6891-6

10.1109/ICME55011.2023.00048

National Natural Science Foundation of China [62201222]; Fundamental Research Funds for the Central Universities [CCNU22QN014, CCNU22XJ034, CCNU22JC007]; National Key Research and Development Program of China [2022YFD1700204]; Collaborative Innovation Center for Informatization and Balanced Development of K-12 Education by MOE [xtzd2021-004]; Hubei Province [xtzd2021-004]

本校为第一且通讯机构

Pseudo-labels are popular in semi-supervised facial expression recognition. Recent methods usually exploit the confidence as the criterion for pseudo-label generation, and utilize the high-confidence pseudo-labels as the ground-truth for training. However, high confidence cannot guarantee the correctness of pseudo-labels. False pseudo-labels can weaken the feature discrimination and degrade recognition performance. In this paper, we propose a Critical Feature Refinement Network (CFRN) to alleviate the interference of false pseudo-labels on the model performance. Specially, a feature dropout mo...