Multi-Centroid Representation Network for Domain Adaptive Person Re-ID
About
Recently, many approaches tackle the Unsupervised Domain Adaptive person re-identification (UDA re-ID) problem through pseudo-label-based contrastive learning. During training, a uni-centroid representation is obtained by simply averaging all the instance features from a cluster with the same pseudo label. However, a cluster may contain images with different identities (label noises) due to the imperfect clustering results, which makes the uni-centroid representation inappropriate. In this paper, we present a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster. MCM can effectively alleviate the issue of label noises by selecting proper positive/negative centroids for the query image. Moreover, we further propose two strategies to improve the contrastive learning process. First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intradomain information by comparing samples only from the same domain. Second, we propose Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples. We integrate MCM, DSCL, and SONI into a unified framework named Multi-Centroid Representation Network (MCRN). Extensive experiments demonstrate the superiority of MCRN over state-of-the-art approaches on multiple UDA re-ID tasks and fully unsupervised re-ID tasks.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Person Re-Identification | Market1501 (test) | Rank-1 Accuracy92.5 | 1264 | |
| Person Re-Identification | Market 1501 | mAP80.8 | 999 | |
| Person Re-Identification | DukeMTMC-reID | Rank-1 Acc83.5 | 648 | |
| Person Re-Identification | MSMT17 (test) | Rank-1 Acc63.6 | 499 | |
| Person Re-Identification | MSMT17 | mAP0.312 | 404 | |
| Person Re-Identification | MSMT17 source: DukeMTMC-reID (test) | Rank-1 Acc67.5 | 83 | |
| Person Re-Identification | DukeMTMC-reID to Market1501 | mAP83.8 | 67 | |
| Person Re-Identification | Market-1501 to MSMT17 | mAP32.8 | 50 | |
| Person Re-Identification | MSMT17 MS | mAP32.8 | 22 | |
| Unsupervised Person Re-identification | Market1501 | mAP80.8 | 21 |