Title | ||
---|---|---|
Hybrid Contrastive Learning with Cluster Ensemble for Unsupervised Person Re-identification |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-031-02444-3_40 | Pattern Recognition |
Keywords | DocType | ISSN |
Unsupervised person ReID, Contrastive learning, Cluster ensemble, Multi-granularity | Conference | 0302-9743 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
He Sun | 1 | 0 | 0.68 |
Mingkun Li | 2 | 0 | 1.69 |
Chun-Guang Li | 3 | 310 | 17.35 |