1 code implementation • 23 May 2023 • Mingkun Li, Peng Xu, Chun-Guang Li, Jun Guo
In this paper, we address a highly challenging yet critical task: unsupervised long-term person re-identification with clothes change.
Ranked #1 on Unsupervised Person Re-Identification on PRCC
Clothes Changing Person Re-Identification Contrastive Learning +3
no code implementations • 7 Feb 2022 • Mingkun Li, Shupeng Cheng, Peng Xu, Xiatian Zhu, Chun-Guang Li, Jun Guo
We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment.
Clustering Unsupervised Long Term Person Re-Identification +2
no code implementations • 28 Jan 2022 • He Sun, Mingkun Li, Chun-Guang Li
The most popular approaches to tackle unsupervised person ReID are usually performing a clustering algorithm to yield pseudo labels at first and then exploit the pseudo labels to train a deep neural network.
Ranked #1 on Unsupervised Person Re-Identification on DukeMTMCreID (MAP metric)
1 code implementation • 15 Jun 2021 • Mingkun Li, Chun-Guang Li, Jun Guo
To be specific, we propose a novel cluster-level contrastive loss to help the siamese network effectively mine the invariance in feature learning with respect to the cluster structure within and between different data augmentation views, respectively.