# Unsupervised Person Re-identification via Softened Similarity Learning

arXiv: https://arxiv.org/abs/2004.03547 · HTML: https://mlsanity.com/paper/2004.03547/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 30 of 75)

- [Cluster Contrast for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.11568/) (2021)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Part-based Pseudo Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2203.14675/) (2022)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification](https://mlsanity.com/paper/2106.06133/) (2021)
- [Implicit Sample Extension for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2204.06892/) (2022)
- [Unsupervised Multi-Source Domain Adaptation for Person Re-Identification](https://mlsanity.com/paper/2104.12961/) (2021)
- [Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.04618/) (2021)
- [VS-Net: Voting with Segmentation for Visual Localization](https://mlsanity.com/paper/2105.10886/) (2021)
- [Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2401.06825/) (2024)
- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id](https://mlsanity.com/paper/2109.14157/) (2021)
- [Transformer for Object Re-Identification: A Survey](https://mlsanity.com/paper/2401.06960/) (2024)
- [Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2106.07846/) (2021)
- [Exploring Visual Context for Weakly Supervised Person Search](https://mlsanity.com/paper/2106.10506/) (2021)
- [Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation](https://mlsanity.com/paper/2103.15685/) (2021)
- [Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID](https://mlsanity.com/paper/2402.00672/) (2024)
- [Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2109.12333/) (2021)
- [Learning to Purification for Unsupervised Person Re-identification](https://mlsanity.com/paper/2204.09931/) (2022)
- [Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2207.13035/) (2022)
- [MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification](https://mlsanity.com/paper/2110.05886/) (2021)
- [Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.05820/) (2022)
- [Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering](https://mlsanity.com/paper/2204.04621/) (2022)
- [Unsupervised Person Re-identification with Stochastic Training Strategy](https://mlsanity.com/paper/2108.06938/) (2021)
- [Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions](https://mlsanity.com/paper/2109.06057/) (2021)
- [Learning Invariance from Generated Variance for Unsupervised Person Re-identification](https://mlsanity.com/paper/2301.00725/) (2023)
- [Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search](https://mlsanity.com/paper/2302.12986/) (2023)
- [Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering](https://mlsanity.com/paper/2103.04580/) (2021)
- [Unsupervised and self-adaptative techniques for cross-domain person re-identification](https://mlsanity.com/paper/2103.11520/) (2021)
- [Context-Aware Unsupervised Clustering for Person Search](https://mlsanity.com/paper/2110.01341/) (2021)

## Abstract (arXiv)

Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information and thus is freely deployed to new scenarios. There are very few studies under this setting, and one of the best approach till now used iterative clustering and classification, so that unlabeled images are clustered into pseudo classes for a classifier to get trained, and the updated features are used for clustering and so on. This approach suffers two problems, namely, the difficulty of determining the number of clusters, and the hard quantization loss in clustering. In this paper, we follow the iterative training mechanism but discard clustering, since it incurs loss from hard quantization, yet its only product, image-level similarity, can be easily replaced by pairwise computation and a softened classification task. With these improvements, our approach becomes more elegant and is more robust to hyper-parameter changes. Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance under the unsupervised re-ID setting.