Papers › AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

AlignedReID: Surpassing Human-Level Performance in Person Re-Identification

22 Nov 2017arXiv:1711.08184archive 2025-07-28

Xuan Zhang, Hao Luo, Xing Fan, Weilai Xiang, Yixiao Sun, Qiqi Xiao, Wei Jiang, Chi Zhang, Jian Sun

In this paper, we propose a novel method called AlignedReID that extracts a global feature which is jointly learned with local features. Global feature learning benefits greatly from local feature learning, which performs an alignment/matching by calculating the shortest path between two sets of local features, without requiring extra supervision. After the joint learning, we only keep the global feature to compute the similarities between images. Our method achieves rank-1 accuracy of 94.4% on Market1501 and 97.8% on CUHK03, outperforming state-of-the-art methods by a large margin. We also evaluate human-level performance and demonstrate that our method is the first to surpass human-level performance on Market1501 and CUHK03, two widely used Person ReID datasets.

PaperPDFCode

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

Code

15 repositories listed; official and paper-mentioned ones first.

Phoebe-star/AlignedReID mentioned on GitHubtf report
abhishirk/Aligned_ReId mentioned on GitHubpytorch report
h4veFunCodin9/Aligned_ReID mentioned on GitHubpytorch report
shubhamtyagii/Aligned_Reid mentioned 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 CUHK-SYSU AlignedReID MAP 94.4 #1 of 3 Archive leaderboard report
Person Re-Identification CUHK-SYSU AlignedReID Rank-1 95.7 #1 of 3 Archive leaderboard report
Person Re-Identification CUHK03 AlignedReID (RK) Rank-1 97.8 #16 of 19 Archive leaderboard report
Person Re-Identification CUHK03 AlignedReID (RK) Rank-10 99.8 #16 of 19 Archive leaderboard report
Person Re-Identification CUHK03 AlignedReID (RK) Rank-5 99.6 #16 of 19 Archive leaderboard report
Person Re-Identification CUHK03-C Aligned++ Rank-1 7.99 #5 of 8 Archive leaderboard report
Person Re-Identification CUHK03-C Aligned++ mAP 4.87 #5 of 8 Archive leaderboard report
Person Re-Identification CUHK03-C Aligned++ mINP 0.56 #5 of 8 Archive leaderboard report
Person Re-Identification Market-1501 AlignedReID (RK) Rank-1 94.4 #78 of 135 Archive leaderboard report
Person Re-Identification Market-1501 AlignedReID (RK) mAP 90.7 #78 of 135 Archive leaderboard report
Person Re-Identification Market-1501-C Aligned++ Rank-1 31.00 #13 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C Aligned++ mAP 10.95 #13 of 22 Archive leaderboard report
Person Re-Identification Market-1501-C Aligned++ mINP 0.32 #13 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