Papers › Compact Network Training for Person ReID

Compact Network Training for Person ReID

15 Oct 2019arXiv:1910.07038archive 2025-07-28

Hussam Lawen, Avi Ben-Cohen, Matan Protter, Itamar Friedman, Lihi Zelnik-Manor

The task of person re-identification (ReID) has attracted growing attention in recent years leading to improved performance, albeit with little focus on real-world applications. Most SotA methods are based on heavy pre-trained models, e.g. ResNet50 (~25M parameters), which makes them less practical and more tedious to explore architecture modifications. In this study, we focus on a small-sized randomly initialized model that enables us to easily introduce architecture and training modifications suitable for person ReID. The outcomes of our study are a compact network and a fitting training regime. We show the robustness of the network by outperforming the SotA on both Market1501 and DukeMTMC. Furthermore, we show the representation power of our ReID network via SotA results on a different task of multi-object tracking.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Multi-Object TrackingPerson Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Person Re-Identification DukeMTMC-reID Compact-ReID (6.4M w/o RK) Rank-1 89.8 #42 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Compact-ReID (6.4M w/o RK) mAP 80.3 #42 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Compact-ReID (2.9M w/o RK) Rank-1 88.8 #51 of 94 Archive leaderboard report
Person Re-Identification DukeMTMC-reID Compact-ReID (2.9M w/o RK) mAP 78.9 #51 of 94 Archive leaderboard report
Person Re-Identification Market-1501 Compact-ReID (6.4M w/o RK) Rank-1 96.2 #23 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Compact-ReID (6.4M w/o RK) mAP 89.7 #23 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Compact-ReID Rank-1 96.2 #24 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Compact-ReID (2.9M w/o RK) Rank-1 95.8 #41 of 135 Archive leaderboard report
Person Re-Identification Market-1501 Compact-ReID (2.9M w/o RK) mAP 88.7 #41 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.

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