# Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification

arXiv: https://arxiv.org/abs/2011.13776 · HTML: https://mlsanity.com/paper/2011.13776/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification](https://mlsanity.com/paper/2110.05886/) (2021)
- [Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification](https://mlsanity.com/paper/2109.05542/) (2021)
- [Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution](https://mlsanity.com/paper/2202.03126/) (2022)
- [Large-scale Fully-Unsupervised Re-Identification](https://mlsanity.com/paper/2307.14278/) (2023)
- [Adaptive Intra-Class Variation Contrastive Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2404.04665/) (2024)
- [Pseudo-label Refinement for Improving Self-Supervised Learning Systems](https://mlsanity.com/paper/2410.14242/) (2024)
- [CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identification](https://mlsanity.com/paper/2508.03064/) (2025)
- [Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation](https://mlsanity.com/paper/2111.14014/) (2021)
- [Unsupervised domain-adaptive person re-identification with multi-camera constraints](https://mlsanity.com/paper/2210.13999/) (2022)
- [CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community](https://mlsanity.com/paper/2407.06485/) (2024)

## Abstract (arXiv)

The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without labor-intensive identity annotations. State-of-the-art unsupervised Re-ID methods assign pseudo labels to unlabeled images in the target domain and learn from these noisy pseudo labels. Recently introduced Mean Teacher Model is a promising way to mitigate the label noise. However, during the training, self-ensembled teacher-student networks quickly converge to a consensus which leads to a local minimum. We explore the possibility of using an asymmetric structure inside neural network to address this problem. First, asymmetric branches are proposed to extract features in different manners, which enhances the feature diversity in appearance signatures. Then, our proposed cross-branch supervision allows one branch to get supervision from the other branch, which transfers distinct knowledge and enhances the weight diversity between teacher and student networks. Extensive experiments show that our proposed method can significantly surpass the performance of previous work on both unsupervised domain adaptation and fully unsupervised Re-ID tasks.