3 papers
cs.CV2023
Cross Architecture Distillation for Face Recognition
Weisong Zhao, Xiangyu Zhu, Zhixiang He +2
Transformers have emerged as the superior choice for face recognition tasks, but their insufficient platform acceleration hinders their application on mobile devices. In contrast,…
cs.CV2023★ 1 cited
Grouped Knowledge Distillation for Deep Face Recognition
Weisong Zhao, Xiangyu Zhu, Kaiwen Guo +2
Compared with the feature-based distillation methods, logits distillation can liberalize the requirements of consistent feature dimension between teacher and student networks, whil…
cs.LG2016
A Self-Paced Regularization Framework for Multi-Label Learning
Changsheng Li, Fan Wei, Junchi Yan +4
In this paper, we propose a novel multi-label learning framework, called Multi-Label Self-Paced Learning (MLSPL), in an attempt to incorporate the self-paced learning strategy into…