Papers › Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification
Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification
He Sun, Mingkun Li, Chun-Guang Li
Unsupervised person re-identification (ReID) aims to match a query image of a pedestrian to the images in gallery set without supervision labels. 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. However, the pseudo labels are noisy and sensitive to the hyper-parameter(s) in clustering algorithm. In this paper, we propose a Hybrid Contrastive Learning (HCL) approach for unsupervised person ReID, which is based on a hybrid between instance-level and cluster-level contrastive loss functions. Moreover, we present a Multi-Granularity Clustering Ensemble based Hybrid Contrastive Learning (MGCE-HCL) approach, which adopts a multi-granularity clustering ensemble strategy to mine priority information among the pseudo positive sample pairs and defines a priority-weighted hybrid contrastive loss for better tolerating the noises in the pseudo positive samples. We conduct extensive experiments on two benchmark datasets Market-1501 and DukeMTMC-reID. Experimental results validate the effectiveness of our proposals.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Unsupervised Person Re-Identification | DukeMTMCreID | MGCE-HCL | MAP | 67.5 | #2 of 2 | Archive leaderboard | report |
| Unsupervised Person Re-Identification | DukeMTMCreID | MGCE-HCL | Rank-1 | 82.5 | #2 of 2 | Archive leaderboard | report |
| Unsupervised Person Re-Identification | Market-1501 | MGCE-HCL | MAP | 79.6 | #13 of 23 | Archive leaderboard | report |
| Unsupervised Person Re-Identification | Market-1501 | MGCE-HCL | Rank-1 | 92.1 | #13 of 23 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections