Papers › DiP: Learning Discriminative Implicit Parts for Person Re-Identification

DiP: Learning Discriminative Implicit Parts for Person Re-Identification

24 Dec 2022arXiv:2212.13906archive 2025-07-28

Dengjie Li, Siyu Chen, Yujie Zhong, Lin Ma

In person re-identification (ReID) tasks, many works explore the learning of part features to improve the performance over global image features. Existing methods explicitly extract part features by either using a hand-designed image division or keypoints obtained with external visual systems. In this work, we propose to learn Discriminative implicit Parts (DiPs) which are decoupled from explicit body parts. Therefore, DiPs can learn to extract any discriminative features that can benefit in distinguishing identities, which is beyond predefined body parts (such as accessories). Moreover, we propose a novel implicit position to give a geometric interpretation for each DiP. The implicit position can also serve as a learning signal to encourage DiPs to be more position-equivariant with the identity in the image. Lastly, an additional DiP weighting is introduced to handle the invisible or occluded situation and further improve the feature representation of DiPs. Extensive experiments show that the proposed method achieves state-of-the-art performance on multiple person ReID benchmarks.

PaperPDFCode

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

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

Person Re-Identification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification CUHK03 detected DiP (without RK) MAP 83.1 #2 of 19 Archive leaderboard report
Person Re-Identification CUHK03 detected DiP (without RK) Rank-1 85.4 #2 of 19 Archive leaderboard report
Person Re-Identification CUHK03 labeled DiP (without RK) MAP 85.7 #3 of 21 Archive leaderboard report
Person Re-Identification CUHK03 labeled DiP (without RK) Rank-1 87 #3 of 21 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DiP (without RK) Rank-1 91.7 #21 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID DiP (without RK) mAP 85.2 #21 of 94 Archive leaderboard report
Person Re-Identification MSMT17 DiP (without RK) Rank-1 87.3 #13 of 43 Archive leaderboard report
Person Re-Identification MSMT17 DiP (without RK) mAP 71.8 #13 of 43 Archive leaderboard report
Person Re-Identification Market-1501 DiP (without RK) Rank-1 95.8 #39 of 135 Archive leaderboard report
Person Re-Identification Market-1501 DiP (without RK) mAP 90.8 #39 of 135 Archive leaderboard report
Person Re-Identification Occluded-DukeMTMC DiP (without RK) Rank-1 71.1 #8 of 32 Archive leaderboard report
Person Re-Identification Occluded-DukeMTMC DiP (without RK) mAP 63.1 #8 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.

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