no code implementations • 26 May 2021 • Shijie Yu, Feng Zhu, Dapeng Chen, Rui Zhao, Haobin Chen, Shixiang Tang, Jinguo Zhu, Yu Qiao
In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts.
no code implementations • CVPR 2021 • Shixiang Tang, Dapeng Chen, Jinguo Zhu, Shijie Yu, Wanli Ouyang
The gradient for update should be close to the gradient of the new task, consistent with the gradients shared by all old tasks, and orthogonal to the space spanned by the gradients specific to the old tasks.
no code implementations • 16 May 2021 • Shijie Yu, Dapeng Chen, Rui Zhao, Haobin Chen, Yu Qiao
Person images captured by surveillance cameras are often occluded by various obstacles, which lead to defective feature representation and harm person re-identification (Re-ID) performance.
1 code implementation • CVPR 2021 • Jinguo Zhu, Shixiang Tang, Dapeng Chen, Shijie Yu, Yakun Liu, Aijun Yang, Mingzhe Rong, Xiaohua Wang
Specifically, we estimate the mutual relation in an anchor-based way and distill the anchor-student relation under the supervision of its corresponding anchor-teacher relation.
Ranked #26 on Knowledge Distillation on ImageNet
2 code implementations • 24 Aug 2020 • Yixiao Ge, Shijie Yu, Dapeng Chen
SDA, a domain-translation-based framework, focuses on carefully translating the source-domain images to the target domain.
no code implementations • CVPR 2020 • Shijie Yu, Shihua Li, Dapeng Chen, Rui Zhao, Junjie Yan, Yu Qiao
To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes.