# Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification

arXiv: https://arxiv.org/abs/2007.13890 · HTML: https://mlsanity.com/paper/2007.13890/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 30 of 31)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [Exploring Visual Context for Weakly Supervised Person Search](https://mlsanity.com/paper/2106.10506/) (2021)
- [Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains](https://mlsanity.com/paper/2101.07308/) (2021)
- [Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification](https://mlsanity.com/paper/2108.09682/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Visible-Infrared Person Re-Identification Using Privileged Intermediate Information](https://mlsanity.com/paper/2209.09348/) (2022)
- [Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser](https://mlsanity.com/paper/2304.06430/) (2023)
- [Holistic Guidance for Occluded Person Re-Identification](https://mlsanity.com/paper/2104.06524/) (2021)
- [MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification](https://mlsanity.com/paper/2110.05886/) (2021)
- [Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations](https://mlsanity.com/paper/2203.01933/) (2022)
- [Approximate Domain Unlearning for Vision-Language Models](https://mlsanity.com/paper/2510.08132/) (2025)
- [Towards Generalizable Person Re-identification with a Bi-stream Generative Model](https://mlsanity.com/paper/2206.09362/) (2022)
- [Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering](https://mlsanity.com/paper/2103.04580/) (2021)
- [Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation](https://mlsanity.com/paper/2304.00792/) (2023)
- [Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.03240/) (2023)
- [Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition](https://mlsanity.com/paper/2207.09767/) (2022)
- [We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline](https://mlsanity.com/paper/2402.00868/) (2024)
- [What Makes You Unique? Attribute Prompt Composition for Object Re-Identification](https://mlsanity.com/paper/2509.18715/) (2025)
- [Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID](https://mlsanity.com/paper/2211.03626/) (2022)
- [Adversarial Self-Attack Defense and Spatial-Temporal Relation Mining for Visible-Infrared Video Person Re-Identification](https://mlsanity.com/paper/2307.03903/) (2023)
- [Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters](https://mlsanity.com/paper/2110.07897/) (2021)
- [TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2111.14290/) (2021)
- [A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification](https://mlsanity.com/paper/2112.12887/) (2021)
- [Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains](https://mlsanity.com/paper/2203.01682/) (2022)
- [Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2201.10212/) (2022)
- [Benchmarking person re-identification datasets and approaches for practical real-world implementations](https://mlsanity.com/paper/2212.09981/) (2022)
- [Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification](https://mlsanity.com/paper/2411.06023/) (2024)
- [Cross-Spectral Attention for Unsupervised RGB-IR Face Verification and Person Re-identification](https://mlsanity.com/paper/2411.19215/) (2024)
- [Evolution of ReID: From Early Methods to LLM Integration](https://mlsanity.com/paper/2506.13039/) (2025)

## Abstract (arXiv)

Person re-identification (ReID) remains a challenging task in many real-word video analytics and surveillance applications, even though state-of-the-art accuracy has improved considerably with the advent of deep learning (DL) models trained on large image datasets. Given the shift in distributions that typically occurs between video data captured from the source and target domains, and absence of labeled data from the target domain, it is difficult to adapt a DL model for accurate recognition of target data. We argue that for pair-wise matchers that rely on metric learning, e.g., Siamese networks for person ReID, the unsupervised domain adaptation (UDA) objective should consist in aligning pair-wise dissimilarity between domains, rather than aligning feature representations. Moreover, dissimilarity representations are more suitable for designing open-set ReID systems, where identities differ in the source and target domains. In this paper, we propose a novel Dissimilarity-based Maximum Mean Discrepancy (D-MMD) loss for aligning pair-wise distances that can be optimized via gradient descent. From a person ReID perspective, the evaluation of D-MMD loss is straightforward since the tracklet information allows to label a distance vector as being either within-class or between-class. This allows approximating the underlying distribution of target pair-wise distances for D-MMD loss optimization, and accordingly align source and target distance distributions. Empirical results with three challenging benchmark datasets show that the proposed D-MMD loss decreases as source and domain distributions become more similar. Extensive experimental evaluation also indicates that UDA methods that rely on the D-MMD loss can significantly outperform baseline and state-of-the-art UDA methods for person ReID without the common requirement for data augmentation and/or complex networks.