Papers › Unsupervised Person Re-identification via Multi-label Classification

Unsupervised Person Re-identification via Multi-label Classification

20 Apr 2020CVPR 2020 6arXiv:2004.09228archive 2025-07-28

Dongkai Wang, Shiliang Zhang

The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels. This paper formulates unsupervised person ReID as a multi-label classification task to progressively seek true labels. Our method starts by assigning each person image with a single-class label, then evolves to multi-label classification by leveraging the updated ReID model for label prediction. The label prediction comprises similarity computation and cycle consistency to ensure the quality of predicted labels. To boost the ReID model training efficiency in multi-label classification, we further propose the memory-based multi-label classification loss (MMCL). MMCL works with memory-based non-parametric classifier and integrates multi-label classification and single-label classification in a unified framework. Our label prediction and MMCL work iteratively and substantially boost the ReID performance. Experiments on several large-scale person ReID datasets demonstrate the superiority of our method in unsupervised person ReID. Our method also allows to use labeled person images in other domains. Under this transfer learning setting, our method also achieves state-of-the-art performance.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

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

ClassificationGeneral ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationPerson Re-IdentificationPredictionTransfer LearningUnsupervised Domain AdaptationUnsupervised Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation Duke to MSMT MMCL mAP 16.2 #7 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT MMCL rank-1 43.6 #7 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT MMCL rank-10 58.9 #7 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to MSMT MMCL rank-5 54.3 #7 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market MMCL mAP 60.4 #13 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market MMCL rank-1 84.4 #13 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market MMCL rank-10 95.0 #13 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Duke to Market MMCL rank-5 92.8 #13 of 26 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke MMCL mAP 51.4 #15 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke MMCL rank-1 72.4 #15 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke MMCL rank-10 85.0 #15 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to Duke MMCL rank-5 82.9 #15 of 25 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT MMCL mAP 15.1 #12 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT MMCL rank-1 40.8 #12 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT MMCL rank-10 56.7 #12 of 17 Archive leaderboard report
Unsupervised Domain Adaptation Market to MSMT MMCL rank-5 51.8 #12 of 17 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.

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