Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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.

Yuhang Wu, Tengteng Huang, Haotian Yao, Chi Zhang, Yuanjie Shao, Chuchu Han, Changxin Gao, Nong Sang• 2021

Related benchmarks

TaskDatasetResultRank
Person Re-IdentificationMarket1501 (test)
Rank-1 Accuracy92.5
1264
Person Re-IdentificationMarket 1501
mAP80.8
999
Person Re-IdentificationDukeMTMC-reID
Rank-1 Acc83.5
648
Person Re-IdentificationMSMT17 (test)
Rank-1 Acc63.6
499
Person Re-IdentificationMSMT17
mAP0.312
404
Person Re-IdentificationMSMT17 source: DukeMTMC-reID (test)
Rank-1 Acc67.5
83
Person Re-IdentificationDukeMTMC-reID to Market1501
mAP83.8
67
Person Re-IdentificationMarket-1501 to MSMT17
mAP32.8
50
Person Re-IdentificationMSMT17 MS
mAP32.8
22
Unsupervised Person Re-identificationMarket1501
mAP80.8
21
Showing 10 of 12 rows

Other info

Follow for update