Papers › Template-Aware Transformer for Person Reidentification
Template-Aware Transformer for Person Reidentification
Yanwei Zheng, Zengrui Zhao, Xiaowei Yu, Dongxiao Yu
Person reidentification (ReID) is a challenging computer vision task for identifying or verifying one or more persons when the faces are not available. In ReID, the indistinguishable background usually affects the model’s perception of the foreground, which reduces the performance of ReID. Generally, the background of the same camera is similar, whereas that of different cameras is quite different. Based on this finding, we propose a template-aware transformer (TAT) method which can learn intersample indistinguishable features by introducing a learnable template for the transformer structure to cut down the model’s attention to regions of the image with low discrimination, including backgrounds and occlusions. In the multiheaded attention module of the encoder, this template directs template-aware attention to indistinguishable features of the image and gradually increases the attention to distinguishable features as the encoder block deepens. We also increase the number of templates using side information considering the characteristics of ReID tasks to adapt the model to backgrounds that vary significantly with different camera IDs. Finally, we demonstrate the validity of our theories using various public data sets and achieve competitive results via a quantitative evaluation.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Person Re-Identification | DukeMTMC-reID | TAT | Rank-1 | 91.5 | #30 of 94 | Archive leaderboard | report |
| Person Re-Identification | DukeMTMC-reID | TAT | mAP | 82.5 | #30 of 94 | Archive leaderboard | report |
| Person Re-Identification | Market-1501 | TAT | Rank-1 | 95.8 | #40 of 135 | Archive leaderboard | report |
| Person Re-Identification | Market-1501 | TAT | mAP | 89.7 | #40 of 135 | Archive leaderboard | report |
| Person Re-Identification | Occluded-DukeMTMC | TAT | Rank-1 | 68.2 | #13 of 32 | Archive leaderboard | report |
| Person Re-Identification | Occluded-DukeMTMC | TAT | mAP | 60.6 | #13 of 32 | 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
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