TY - GEN
T1 - RamFace
T2 - 2021 IEEE International Joint Conference on Biometrics, IJCB 2021
AU - Yang, Zhanjia
AU - Zhu, Xiangping
AU - Jiang, Changyuan
AU - Liu, Wenshuang
AU - Shen, Linlin
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/8/4
Y1 - 2021/8/4
N2 - Recent studies show that there exist significant racial bias among state-of-The-Art (SOTA) face recognition algorithms, i.e., the accuracy for Caucasian is consistently higher than that for other races like African and Asian. To mitigate racial bias, we propose the race adaptive margin based face recognition (RamFace) model, designed under the multi-Task learning framework with the race classification as the auxiliary task. The experiments show that the race classification task can enforce the model to learn the racial features and thus improve the discriminability of the extracted feature representations. In addition, a racial bias robust loss function, i.e., race adaptive margin loss, is proposed such that different optimal margins can be automatically derived for different races in training the model, which further mitigates the racial bias. The experimental results show that on RFW dataset, our model not only achieves SOTA face recognition accuracy but also mitigates the racial bias problem. Besides, RamFace is also tested on several public face recognition evaluation benchmarks, i.e., LFW, CPLFW and CALFW, and achieves better performance than the commonly used face recognition methods, which justifies the generalization capability of RamFace.
AB - Recent studies show that there exist significant racial bias among state-of-The-Art (SOTA) face recognition algorithms, i.e., the accuracy for Caucasian is consistently higher than that for other races like African and Asian. To mitigate racial bias, we propose the race adaptive margin based face recognition (RamFace) model, designed under the multi-Task learning framework with the race classification as the auxiliary task. The experiments show that the race classification task can enforce the model to learn the racial features and thus improve the discriminability of the extracted feature representations. In addition, a racial bias robust loss function, i.e., race adaptive margin loss, is proposed such that different optimal margins can be automatically derived for different races in training the model, which further mitigates the racial bias. The experimental results show that on RFW dataset, our model not only achieves SOTA face recognition accuracy but also mitigates the racial bias problem. Besides, RamFace is also tested on several public face recognition evaluation benchmarks, i.e., LFW, CPLFW and CALFW, and achieves better performance than the commonly used face recognition methods, which justifies the generalization capability of RamFace.
UR - http://www.scopus.com/inward/record.url?scp=85113320286&partnerID=8YFLogxK
U2 - 10.1109/IJCB52358.2021.9484352
DO - 10.1109/IJCB52358.2021.9484352
M3 - Conference contribution
AN - SCOPUS:85113320286
T3 - 2021 IEEE International Joint Conference on Biometrics, IJCB 2021
BT - 2021 IEEE International Joint Conference on Biometrics, IJCB 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 4 August 2021 through 7 August 2021
ER -