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

TL;DR

This paper introduces an unsupervised vehicle re-identification framework that combines multi-granularity CNN features with group contrastive learning to improve domain adaptation across different surveillance datasets.

Contribution

It proposes a novel combination of multi-granularity CNN representations and group contrastive learning for effective unsupervised domain adaptation in vehicle ReID.

Findings

Outperforms existing state-of-the-art methods in unsupervised vehicle ReID.

Effectively generates pseudo labels for unlabeled target datasets.

Demonstrates robustness across multiple large-scale datasets.

Abstract

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.