Papers › Learning to Disentangle Scenes for Person Re-identification

Learning to Disentangle Scenes for Person Re-identification

10 Nov 2021arXiv:2111.05476archive 2025-07-28

Xianghao Zang, Ge Li, Wei Gao, Xiujun Shu

There are many challenging problems in the person re-identification (ReID) task, such as the occlusion and scale variation. Existing works usually tried to solve them by employing a one-branch network. This one-branch network needs to be robust to various challenging problems, which makes this network overburdened. This paper proposes to divide-and-conquer the ReID task. For this purpose, we employ several self-supervision operations to simulate different challenging problems and handle each challenging problem using different networks. Concretely, we use the random erasing operation and propose a novel random scaling operation to generate new images with controllable characteristics. A general multi-branch network, including one master branch and two servant branches, is introduced to handle different scenes. These branches learn collaboratively and achieve different perceptive abilities. In this way, the complex scenes in the ReID task are effectively disentangled, and the burden of each branch is relieved. The results from extensive experiments demonstrate that the proposed method achieves state-of-the-art performances on three ReID benchmarks and two occluded ReID benchmarks. Ablation study also shows that the proposed scheme and operations significantly improve the performance in various scenes. The code is available at https://git.openi.org.cn/zangxh/LDS.git.

PaperPDFConference PDFCode

Code

deropty/LDS officialmentioned on GitHubpytorch 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.

Code Syntology ran Syntology

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

Tasks

Person Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification DukeMTMC-reID LDS (ResNet50 + RK) Rank-1 92.91 #8 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID LDS (ResNet50 + RK) mAP 91.0 #8 of 94 Archive leaderboard report
Person Re-Identification MSMT17 LDS (ResNet50+RK) Rank-1 88.35 #5 of 43 Archive leaderboard report
Person Re-Identification MSMT17 LDS (ResNet50+RK) mAP 79.09 #5 of 43 Archive leaderboard report
Person Re-Identification Market-1501 LDS (ResNet50 + RK) Rank-1 96.17 #25 of 135 Archive leaderboard report
Person Re-Identification Market-1501 LDS (ResNet50 + RK) mAP 94.89 #25 of 135 Archive leaderboard report
Person Re-Identification Occluded-DukeMTMC LDS Rank-1 64.3 #19 of 32 Archive leaderboard report
Person Re-Identification Occluded-DukeMTMC LDS mAP 55.7 #19 of 32 Archive leaderboard report
Person Re-Identification P-DukeMTMC-reID LDS Rank-1 91.96 #2 of 2 Archive leaderboard report
Person Re-Identification P-DukeMTMC-reID LDS Rank-10 96.39 #2 of 2 Archive leaderboard report
Person Re-Identification P-DukeMTMC-reID LDS Rank-5 95.28 #2 of 2 Archive leaderboard report
Person Re-Identification P-DukeMTMC-reID LDS mAP 82.93 #2 of 2 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.

Methods

Random ErasingRandom Scaling

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