TY - GEN
T1 - UniFace
T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
AU - Zhou, Jiancan
AU - Jia, Xi
AU - Li, Qiufu
AU - Shen, Linlin
AU - Duan, Jinming
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - As a widely used loss function in deep face recognition, the softmax loss cannot guarantee that the minimum positive sample-to-class similarity is larger than the maximum negative sample-to-class similarity. As a result, no unified threshold is available to separate positive sample-to-class pairs from negative sample-to-class pairs. To bridge this gap, we design a UCE (Unified Cross-Entropy) loss for face recognition model training, which is built on the vital constraint that all the positive sample-to-class similarities shall be larger than the negative ones. Our UCE loss can be integrated with margins for a further performance boost. The face recognition model trained with the proposed UCE loss, UniFace, was intensively evaluated using a number of popular public datasets like MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace. Experimental results show that our approach outperforms SOTA methods like SphereFace, CosFace, ArcFace, Partial FC, etc. Especially, till the submission of this work (Mar. 8, 2023), the proposed UniFace achieves the highest TAR@MR-All on the academic track of the MFR-ongoing challenge. Code is publicly available.
AB - As a widely used loss function in deep face recognition, the softmax loss cannot guarantee that the minimum positive sample-to-class similarity is larger than the maximum negative sample-to-class similarity. As a result, no unified threshold is available to separate positive sample-to-class pairs from negative sample-to-class pairs. To bridge this gap, we design a UCE (Unified Cross-Entropy) loss for face recognition model training, which is built on the vital constraint that all the positive sample-to-class similarities shall be larger than the negative ones. Our UCE loss can be integrated with margins for a further performance boost. The face recognition model trained with the proposed UCE loss, UniFace, was intensively evaluated using a number of popular public datasets like MFR, IJB-C, LFW, CFP-FP, AgeDB, and MegaFace. Experimental results show that our approach outperforms SOTA methods like SphereFace, CosFace, ArcFace, Partial FC, etc. Especially, till the submission of this work (Mar. 8, 2023), the proposed UniFace achieves the highest TAR@MR-All on the academic track of the MFR-ongoing challenge. Code is publicly available.
UR - http://www.scopus.com/inward/record.url?scp=85185874724&partnerID=8YFLogxK
U2 - 10.1109/ICCV51070.2023.01895
DO - 10.1109/ICCV51070.2023.01895
M3 - Conference contribution
AN - SCOPUS:85185874724
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 20673
EP - 20682
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 2 October 2023 through 6 October 2023
ER -