LKA-ReID:Vehicle Re-Identification with Large Kernel Attention

TL;DR

This paper introduces LKA-ReID, a vehicle re-identification model that uses large kernel attention and hybrid channel attention to effectively capture global and local features, improving accuracy without extra annotations.

Contribution

The paper proposes a novel large kernel attention mechanism combined with hybrid channel attention for vehicle Re-ID, reducing reliance on additional annotations and lowering computational costs.

Findings

Achieved 86.65% mAP on VeRi-776 dataset

Reached 98.03% Rank-1 accuracy

Demonstrated effectiveness of LKA-ReID in vehicle re-identification

Abstract

With the rapid development of intelligent transportation systems and the popularity of smart city infrastructure, Vehicle Re-ID technology has become an important research field. The vehicle Re-ID task faces an important challenge, which is the high similarity between different vehicles. Existing methods use additional detection or segmentation models to extract differentiated local features. However, these methods either rely on additional annotations or greatly increase the computational cost. Using attention mechanism to capture global and local features is crucial to solve the challenge of high similarity between classes in vehicle Re-ID tasks. In this paper, we propose LKA-ReID with large kernel attention. Specifically, the large kernel attention (LKA) utilizes the advantages of self-attention and also benefits from the advantages of convolution, which can extract the global and local features of the vehicle more comprehensively. We also introduce hybrid channel attention (HCA) combines channel attention with spatial information, so that the model can better focus on channels and feature regions, and ignore background and other disturbing information. Experiments on VeRi-776 dataset demonstrated the effectiveness of LKA-ReID, with mAP reaches 86.65% and Rank-1 reaches 98.03%.