S
Shijie Yu
Researcher at Chinese Academy of Sciences
Publications - 12
Citations - 158
Shijie Yu is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Mutual information & Relation (database). The author has an hindex of 3, co-authored 11 publications receiving 32 citations.
Papers
More filters
Proceedings ArticleDOI
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification
TL;DR: Wang et al. as discussed by the authors proposed a two-branch network named Biometric-Clothes Network (BC-Net) which can effectively integrate biometric and clothes feature for re-id under their setting.
Proceedings ArticleDOI
Layerwise Optimization by Gradient Decomposition for Continual Learning
TL;DR: This work decomposed the gradient of an old task into a part shared by all old tasks and a part specific to that task, and performs optimization for the gradients of each layer separately rather than the concatenation of all gradients as in previous works.
Posted Content
Complementary Relation Contrastive Distillation
Jinguo Zhu,Shixiang Tang,Dapeng Chen,Shijie Yu,Yakun Liu,Aijun Yang,Mingzhe Rong,Xiaohua Wang +7 more
TL;DR: This paper proposes a novel knowledge distillation method, namely Complementary Relation Contrastive Distillation (CRCD), to transfer the structural knowledge from the teacher to the student and estimates the mutual relation in an anchor-based way and distill the anchorstudent relation under the supervision of its corresponding anchor-teacher relation.
Proceedings ArticleDOI
Complementary Relation Contrastive Distillation
Jinguo Zhu,Shixiang Tang,Dapeng Chen,Shijie Yu,Yakun Liu,Mingzhe Rong,Aijun Yang,Xiaohua Wang +7 more
TL;DR: Zhang et al. as discussed by the authors proposed complementary relation contrastive distillation (CRCD) to transfer the structural knowledge from the teacher to the student by estimating the mutual relation in an anchor-based way and distill the anchor-student relation under the supervision of its corresponding anchor-teacher relation.
Posted Content
Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID
Yixiao Ge,Shijie Yu,Dapeng Chen +2 more
TL;DR: This technical report presents a proposed solution based on Structured Domain Adaptation and Mutual Mean-Teaching frameworks to mitigate the label noise by modeling inter-sample relations across two domains and maintaining the instance discrimination.