Papers › MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID
Jianyang Gu, Kai Wang, Hao Luo, Chen Chen, Wei Jiang, Yuqiang Fang, Shanghang Zhang, Yang You, Jian Zhao
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance. Previous works explore new optimizing targets and search spaces for NAS ReID, yet they neglect the difference of training schemes between image classification and ReID. In this work, we propose a novel Twins Contrastive Mechanism (TCM) to provide more appropriate supervision for ReID architecture search. TCM reduces the category overlaps between the training and validation data, and assists NAS in simulating real-world ReID training schemes. We then design a Multi-Scale Interaction (MSI) search space to search for rational interaction operations between multi-scale features. In addition, we introduce a Spatial Alignment Module (SAM) to further enhance the attention consistency confronted with images from different sources. Under the proposed NAS scheme, a specific architecture is automatically searched, named as MSINet. Extensive experiments demonstrate that our method surpasses state-of-the-art ReID methods on both in-domain and cross-domain scenarios. Source code available in https://github.com/vimar-gu/MSINet.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Person Re-Identification | MSMT17 | MSINet (2.3M w/o RK) | Rank-1 | 81 | #32 of 43 | Archive leaderboard | report |
| Person Re-Identification | MSMT17 | MSINet (2.3M w/o RK) | mAP | 59.6 | #32 of 43 | Archive leaderboard | report |
| Person Re-Identification | Market-1501 | MSINet (2.3M w/o RK) | Rank-1 | 95.3 | #63 of 135 | Archive leaderboard | report |
| Person Re-Identification | Market-1501 | MSINet (2.3M w/o RK) | mAP | 89.6 | #63 of 135 | Archive leaderboard | report |
| Vehicle Re-Identification | VeRi-776 | MSINet (2.3M w/o RK) | Rank-1 | 96.8 | #14 of 17 | Archive leaderboard | report |
| Vehicle Re-Identification | VeRi-776 | MSINet (2.3M w/o RK) | mAP | 78.8 | #14 of 17 | Archive leaderboard | report |
| Vehicle Re-Identification | VehicleID Large | MSINet (2.3M w/o RK) | Rank-1 | 77.9 | #8 of 10 | Archive leaderboard | report |
| Vehicle Re-Identification | VehicleID Large | MSINet (2.3M w/o RK) | Rank-5 | 91.7 | #8 of 10 | 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