Saved in:
Bibliographic Details
Main Authors: Lu, Liping, Fu, Zihao, Chu, Duanfeng, Wang, Wei, Xu, Bingrong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.16815
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910842154385408
author Lu, Liping
Fu, Zihao
Chu, Duanfeng
Wang, Wei
Xu, Bingrong
author_facet Lu, Liping
Fu, Zihao
Chu, Duanfeng
Wang, Wei
Xu, Bingrong
contents Vehicle re-identification (Re-ID) is a crucial task in intelligent transportation systems (ITS), aimed at retrieving and matching the same vehicle across different surveillance cameras. Numerous studies have explored methods to enhance vehicle Re-ID by focusing on semantic enhancement. However, these methods often rely on additional annotated information to enable models to extract effective semantic features, which brings many limitations. In this work, we propose a CLIP-based Semantic Enhancement Network (CLIP-SENet), an end-to-end framework designed to autonomously extract and refine vehicle semantic attributes, facilitating the generation of more robust semantic feature representations. Inspired by zero-shot solutions for downstream tasks presented by large-scale vision-language models, we leverage the powerful cross-modal descriptive capabilities of the CLIP image encoder to initially extract general semantic information. Instead of using a text encoder for semantic alignment, we design an adaptive fine-grained enhancement module (AFEM) to adaptively enhance this general semantic information at a fine-grained level to obtain robust semantic feature representations. These features are then fused with common Re-ID appearance features to further refine the distinctions between vehicles. Our comprehensive evaluation on three benchmark datasets demonstrates the effectiveness of CLIP-SENet. Our approach achieves new state-of-the-art performance, with 92.9% mAP and 98.7% Rank-1 on VeRi-776 dataset, 90.4% Rank-1 and 98.7% Rank-5 on VehicleID dataset, and 89.1% mAP and 97.9% Rank-1 on the more challenging VeRi-Wild dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2502_16815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification
Lu, Liping
Fu, Zihao
Chu, Duanfeng
Wang, Wei
Xu, Bingrong
Computer Vision and Pattern Recognition
Vehicle re-identification (Re-ID) is a crucial task in intelligent transportation systems (ITS), aimed at retrieving and matching the same vehicle across different surveillance cameras. Numerous studies have explored methods to enhance vehicle Re-ID by focusing on semantic enhancement. However, these methods often rely on additional annotated information to enable models to extract effective semantic features, which brings many limitations. In this work, we propose a CLIP-based Semantic Enhancement Network (CLIP-SENet), an end-to-end framework designed to autonomously extract and refine vehicle semantic attributes, facilitating the generation of more robust semantic feature representations. Inspired by zero-shot solutions for downstream tasks presented by large-scale vision-language models, we leverage the powerful cross-modal descriptive capabilities of the CLIP image encoder to initially extract general semantic information. Instead of using a text encoder for semantic alignment, we design an adaptive fine-grained enhancement module (AFEM) to adaptively enhance this general semantic information at a fine-grained level to obtain robust semantic feature representations. These features are then fused with common Re-ID appearance features to further refine the distinctions between vehicles. Our comprehensive evaluation on three benchmark datasets demonstrates the effectiveness of CLIP-SENet. Our approach achieves new state-of-the-art performance, with 92.9% mAP and 98.7% Rank-1 on VeRi-776 dataset, 90.4% Rank-1 and 98.7% Rank-5 on VehicleID dataset, and 89.1% mAP and 97.9% Rank-1 on the more challenging VeRi-Wild dataset.
title CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.16815