Papers › Unsupervised Pre-training for Person Re-identification

Unsupervised Pre-training for Person Re-identification

7 Dec 2020CVPR 2021 1arXiv:2012.03753archive 2025-07-28

Dengpan Fu, Dongdong Chen, Jianmin Bao, Hao Yang, Lu Yuan, Lei Zhang, Houqiang Li, Dong Chen

In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation. This is to address the problem that all existing person Re-ID datasets are all of limited scale due to the costly effort required for data annotation. Previous research tries to leverage models pre-trained on ImageNet to mitigate the shortage of person Re-ID data but suffers from the large domain gap between ImageNet and person Re-ID data. LUPerson is an unlabeled dataset of 4M images of over 200K identities, which is 30X larger than the largest existing Re-ID dataset. It also covers a much diverse range of capturing environments (eg, camera settings, scenes, etc.). Based on this dataset, we systematically study the key factors for learning Re-ID features from two perspectives: data augmentation and contrastive loss. Unsupervised pre-training performed on this large-scale dataset effectively leads to a generic Re-ID feature that can benefit all existing person Re-ID methods. Using our pre-trained model in some basic frameworks, our methods achieve state-of-the-art results without bells and whistles on four widely used Re-ID datasets: CUHK03, Market1501, DukeMTMC, and MSMT17. Our results also show that the performance improvement is more significant on small-scale target datasets or under few-shot setting.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

DengpanFu/LUPerson officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Large-Scale Pre-training for Person Re-identification with Noisy Labels (arXiv:2203.16533; that paper's own run record: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified) and Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for... (arXiv:2303.17602; that paper's own run record: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationPerson Re-IdentificationUnsupervised Pre-training

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03 Unsupervised Pre-training (ResNet50+BDB) MAP 79.6 #9 of 19 Archive leaderboard report
Person Re-Identification CUHK03 Unsupervised Pre-training (ResNet50+BDB) Rank-1 81.9 #9 of 19 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Unsupervised Pre-training (ResNet101+RK) Rank-1 93.99 #4 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Unsupervised Pre-training (ResNet101+RK) mAP 92.77 #4 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Unsupervised Pre-training (ResNet101+MGN) Rank-1 91.9 #25 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Unsupervised Pre-training (ResNet101+MGN) mAP 84.1 #25 of 94 Archive leaderboard report
Person Re-Identification MSMT17 Unsupervised Pre-training (ResNet101+MGN) Rank-1 86.6 #15 of 43 Archive leaderboard report
Person Re-Identification MSMT17 Unsupervised Pre-training (ResNet101+MGN) mAP 68.8 #15 of 43 Archive leaderboard report
Person Re-Identification Market-1501 Unsupervised Pre-training (ResNet101+MGN) Rank-1 97 #5 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Unsupervised Pre-training (ResNet101+MGN) mAP 92 #5 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Unsupervised Pre-training (ResNet101+RK) mAP 96.21 #126 of 135 Archive leaderboard report
Person Re-Identification Market-1501-C LUPerson Rank-1 32.22 #22 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C LUPerson mAP 10.37 #22 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C LUPerson mINP 0.29 #22 of 22 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