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

arXiv: https://arxiv.org/abs/2410.21667 · HTML: https://mlsanity.com/paper/2410.21667/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification](https://mlsanity.com/paper/2001.01526/) (2020)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [Unsupervised Vehicle Re-identification with Progressive Adaptation](https://mlsanity.com/paper/2006.11486/) (2020)
- [Weighted Bilinear Coding over Salient Body Parts for Person Re-identification](https://mlsanity.com/paper/1803.08580/) (2018)
- [Distribution Context Aware Loss for Person Re-identification](https://mlsanity.com/paper/1911.07273/) (2019)
- [Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption](https://mlsanity.com/paper/1811.12751/) (2018)

## Abstract (arXiv)

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.