Papers › Revisiting Multi-Granularity Representation via Group Contrastive Learning for...

Revisiting Multi-Granularity Representation via Group Contrastive Learning for Unsupervised Vehicle Re-identification

29 Oct 2024arXiv:2410.21667archive 2025-07-28

Zhigang Chang, Shibao Zheng

Vehicle re-identification (Vehicle ReID) aims at retrieving vehicle images across disjoint surveillance camera views. The majority of vehicle ReID research is heavily reliant upon supervisory labels from specific human-collected datasets for training. When applied to the large-scale real-world scenario, these models will experience dreadful performance declines due to the notable domain discrepancy between the source dataset and the target. To address this challenge, in this paper, we propose an unsupervised vehicle ReID framework (MGR-GCL). It integrates a multi-granularity CNN representation for learning discriminative transferable features and a contrastive learning module responsible for efficient domain adaptation in the unlabeled target domain. Specifically, after training the proposed Multi-Granularity Representation (MGR) on the labeled source dataset, we propose a group contrastive learning module (GCL) to generate pseudo labels for the target dataset, facilitating the domain adaptation process. We conducted extensive experiments and the results demonstrated our superiority against existing state-of-the-art methods.

PaperPDF

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

Contrastive LearningDomain AdaptationUnsupervised Domain AdaptationUnsupervised Vehicle Re-IdentificationVehicle Re-Identification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation VehicleID to VeRi-776 MGR-GCL Rank-1 79.29 #3 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 MGR-GCL Rank-10 - #3 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 MGR-GCL Rank-5 87.95 #3 of 14 Archive leaderboard report
Unsupervised Domain Adaptation VehicleID to VeRi-776 MGR-GCL mAP 48.73 #3 of 14 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large MGR-GCL R-1 42.83 #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large MGR-GCL R-10 - #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large MGR-GCL R-5 64.36 #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Large MGR-GCL mAP 47.59 #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium MGR-GCL R-1 45.88 #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium MGR-GCL R-10 - #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium MGR-GCL R-5 67.65 #5 of 13 Archive leaderboard report
Unsupervised Domain Adaptation Veri-776 to VehicleID Medium MGR-GCL mAP 50.56 #5 of 13 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

Contrastive Learning

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