activity
20182021
most citedMutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

392 citations · 447 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV20214 cited

Layerwise Optimization by Gradient Decomposition for Continual Learning

Shixiang Tang, Dapeng Chen, Jinguo Zhu +2

Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget th…

cs.CV202112 cited

Neighbourhood-guided Feature Reconstruction for Occluded Person Re-Identification

Shijie Yu, Dapeng Chen, Rui Zhao +2

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) per…

cs.CV2021

Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification

Shijie Yu, Feng Zhu, Dapeng Chen +5

Recent years have witnessed significant progress in person re-identification (ReID). However, current ReID approaches still suffer from considerable performance degradation when un…

cs.CV20211 cited

Complementary Relation Contrastive Distillation

Jinguo Zhu, Shixiang Tang, Dapeng Chen +5

Knowledge distillation aims to transfer representation ability from a teacher model to a student model. Previous approaches focus on either individual representation distillation o…

cs.CV20201 cited

Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks

Kun Yuan, Quanquan Li, Dapeng Chen +2

One practice of employing deep neural networks is to apply the same architecture to all the input instances. However, a fixed architecture may not be representative enough for data…

cs.CV2020

Continual Representation Learning for Biometric Identification

Bo Zhao, Shixiang Tang, Dapeng Chen +2

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly i…