Attribute-guided Feature Extraction and Augmentation Robust Learning for Vehicle Re-identification

TL;DR

This paper presents a multi-guided learning approach for vehicle re-identification that leverages attribute information and novel data augmentation techniques to improve robustness and matching accuracy in complex scenarios.

Contribution

It introduces a new attribute-guided feature extraction method combined with two novel random augmentation strategies and a group re-ranking technique for enhanced vehicle re-identification.

Findings

Achieved 66.83% mAP and 76.05% rank-1 accuracy on the CVPR 2020 AI City Challenge dataset.

Demonstrated improved robustness and accuracy over existing methods.

Validated effectiveness of attribute constraints and re-ranking strategies.

Abstract

Vehicle re-identification is one of the core technologies of intelligent transportation systems and smart cities, but large intra-class diversity and inter-class similarity poses great challenges for existing method. In this paper, we propose a multi-guided learning approach which utilizing the information of attributes and meanwhile introducing two novel random augments to improve the robustness during training. What's more, we propose an attribute constraint method and group re-ranking strategy to refine matching results. Our method achieves mAP of 66.83% and rank-1 accuracy 76.05% in the CVPR 2020 AI City Challenge.