1 code implementation • 21 May 2024 • Weijia Fan, Jiajun Wen, Xi Jia, Linlin Shen, Jiancan Zhou, Qiufu Li
When the prototypes are updated using the facial sample feature gradients in the model training, they are prone to being pulled away from the class center by the hard samples, resulting in decreased overall model performance.
no code implementations • 12 Mar 2024 • Qiufu Li, Xi Jia, Jiancan Zhou, Linlin Shen, Jinming Duan
We also propose the uniform classification accuracy as a metric to measure the model's performance in uniform classification.
1 code implementation • ICCV 2023 • Jiancan Zhou, Xi Jia, Qiufu Li, Linlin Shen, Jinming Duan
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.