Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Zhigang Chang, Shibao Zheng

TL;DR

An unsupervised vehicle ReID framework that 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 is proposed.

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.

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

TL;DR

An unsupervised vehicle ReID framework that 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 is proposed.

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.

Paper Structure

This paper contains 15 sections, 6 equations, 1 figure, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. Contrastive Learning
  4. Unsupervised Domain Adaptation
  5. Proposed Method
  6. Problem Definition
  7. Fully Supervised Multi-Granularity Representation Learning
  8. Unsupervised Pseudo Label Generation
  9. Group Contrastive Feature Learning
  10. Experiments
  11. Datasets and Evaluation Metrics
  12. Implementation Details
  13. Comparison with the State-of-the-arts
  14. Ablation Studies
  15. conclusion

Figures (1)

  • Figure 1: The framework of MGR-GCL. It basically contains two stages. Stage 1 is a supervised multi-granularity representation learning process in the source domain. Stage 2 illustrates the unsupervised domain adaptation stage by group contrastive learning.