Papers › Person Re-identification via Attention Pyramid

Person Re-identification via Attention Pyramid

11 Aug 2021arXiv:2108.05340archive 2025-07-28

Guangyi Chen, Tianpei Gu, Jiwen Lu, Jin-An Bao, Jie zhou

In this paper, we propose an attention pyramid method for person re-identification. Unlike conventional attention-based methods which only learn a global attention map, our attention pyramid exploits the attention regions in a multi-scale manner because human attention varies with different scales. Our attention pyramid imitates the process of human visual perception which tends to notice the foreground person over the cluttered background, and further focus on the specific color of the shirt with close observation. Specifically, we describe our attention pyramid by a "split-attend-merge-stack" principle. We first split the features into multiple local parts and learn the corresponding attentions. Then, we merge local attentions and stack these merged attentions with the residual connection as an attention pyramid. The proposed attention pyramid is a lightweight plug-and-play module that can be applied to off-the-shelf models. We implement our attention pyramid method in two different attention mechanisms including channel-wise attention and spatial attention. We evaluate our method on four largescale person re-identification benchmarks including Market-1501, DukeMTMC, CUHK03, and MSMT17. Experimental results demonstrate the superiority of our method, which outperforms the state-of-the-art methods by a large margin with limited computational cost.

PaperPDFCode

Code

chengy12/apnet officialmentioned in paperpytorch 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 APNet-C Rank-1 90.4 #37 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID APNet-C mAP 81.5 #37 of 94 Archive leaderboard report
Person Re-Identification MSMT17 APNet-C(ResNet50) Rank-1 83.7 #26 of 43 Archive leaderboard report
Person Re-Identification MSMT17 APNet-C(ResNet50) mAP 63.5 #26 of 43 Archive leaderboard report
Person Re-Identification Market-1501 APNet-C Rank-1 96.2 #21 of 135 Archive leaderboard report
Person Re-Identification Market-1501 APNet-C mAP 90.5 #21 of 135 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

Residual Connection

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