Global-Local Complementary Representation Network for Vehicle Re-Identification
Loading...
Date
2025
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Vehicle Re-Identification (ReID) aims to retrieve images of the same vehicle across multiple non-overlapping cameras. Despite recent advances driven by deep learning, this problem continues to pose challenging due to inter-class similarity and intraclass variation. To address these challenges, we propose a Global-Local Complementary Representation Network (GLCR-Net), which combines global and local features to enhance vehicle ReID accuracy. The global branch employs group convolutions to mitigate overfitting, reduce parameters, and extract comprehensive global features. Meanwhile, the local branch uses a keypoint prediction model to generate keypoint feature maps that are integrated with global features, emphasizing critical regions. Additionally, a Class Activation Mapping (CAM)-based complementary feature learning module is employed to captures features from non-keypoint regions, enriching the feature representation. Experimental results on the VeRi-776 and VehicleID datasets demonstrate that GLCR-Net surpasses state-of-the-art methods in accuracy and generalization. Ablation studies further confirm the effectiveness of group convolutions, keypoint feature integration, and complementary feature learning.
Description
CCS Concepts: Computing methodologies → Supervised learning by classification
@inproceedings{10.2312:pg.20251272,
booktitle = {Pacific Graphics Conference Papers, Posters, and Demos},
editor = {Christie, Marc and Han, Ping-Hsuan and Lin, Shih-Syun and Pietroni, Nico and Schneider, Teseo and Tsai, Hsin-Ruey and Wang, Yu-Shuen and Zhang, Eugene},
title = {{Global-Local Complementary Representation Network for Vehicle Re-Identification}},
author = {Deng, Mingchen and Tang, Ziyao and Xiao, Guoqiang},
year = {2025},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-295-0},
DOI = {10.2312/pg.20251272}
}