Junhui Yin

Junhui Yin

Auto-generated profile, based on publicly available information

Junhui Yin

Beijing University of Posts and Telecommunications, Beijing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 April 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
JYJunhui Yin
Junhui Yin
XZXinyu Zhang
Xinyu Zhang
ZMZhanyu Ma
Zhanyu Ma
JGJun Guo
Jun Guo
YLYifan Liu
Yifan Liu
Recently, clustering-based methods have been the dominant solution for unsupervised person re-identification (ReID). Memory-based contrastive learning is widely used for its effectiveness in unsupervised representation learning. However, we find that the inaccurate cluster proxies and the momentum updating strategy do harm to the contrastive learning system. In this paper, we propose a real-time memory updating strategy (RTMem) to update the cluster centroid with a randomly sampled instance feature in the current mini-batch without momentum. Compared to the method that calculates the mean feature vectors as the cluster centroid and updating it with momentum, RTMem enables the features to be up-to-date for each cluster. Based on RTMem, we propose two contrastive losses, i.e ., sample-to-instance and sample-to-cluster, to align the relationships between samples to each cluster and to all outliers not belonging to any other clusters. On the one hand, sample-to-instance loss explores the sample relationships of the whole dataset to enhance the capability of density-based clustering algorithm, which relies on similarity measurement for the instance-level images. On the other hand, with pseudo-labels generated by the density-based clustering algorithm, sample-to-cluster loss enforces the sample to be close to its cluster proxy while being far from other proxies. With the simple RTMem contrastive learning strategy, the performance of the corresponding baseline is improved by 9.3% on Market-1501 dataset. Our method consistently outperforms state-of-the-art unsupervised learning person ReID methods on three benchmark datasets. Code is made available at https://github.com/PRIS-CV/RTMem.

12 April 2022 in Pattern Recognition
Verified
Journal Article
Closed access
JYJunhui Yin
Junhui Yin
JXJiyang Xie
Jiyang Xie
ZMZhanyu Ma
Zhanyu Ma
JGJun Guo
Jun Guo

18 January 2025 in Pattern Recognition
Verified
Journal Article
Closed access
JYJunhui Yin
Junhui Yin
XZXinyu Zhang
Xinyu Zhang
LWLin Wu
Lin Wu
XWXiaojie Wang
Xiaojie Wang

17 June 2025 in Pattern Recognition
Verified
Journal Article
Closed access
JYJunhui Yin
Junhui Yin
WYWei Yin
Wei Yin
HCHao Chen
Hao Chen
XRXuqian Ren
Xuqian Ren
ZMZhanyu Ma
Zhanyu Ma
YLYifan Liu
Yifan Liu

27 October 2025
Verified
Conference Paper
Open access
YHYizhi Hu
Yizhi Hu
ZTZezhao Tian
Zezhao Tian
XQXingqun Qi
Xingqun Qi
CSChen Su
Chen Su
BYBingkun Yang
Bingkun Yang
ZSZhenan Sun
Zhenan Sun

25 August 2026 in Pattern Recognition
Verified
Journal Article
Closed access
JYJunhui Yin
Junhui Yin
NPNan Pu
Nan Pu
HJHuixing Jiang
Huixing Jiang
WCWei Chen
Wei Chen
XWXiaojie Wang
Xiaojie Wang
ZZZhun Zhong
Zhun Zhong