# Hard Samples Rectification for Unsupervised Cross-domain Person Re-identification

arXiv: https://arxiv.org/abs/2106.07204 · HTML: https://mlsanity.com/paper/2106.07204/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 14 Jun 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [Unsupervised Person Re-identification: Clustering and Fine-tuning](https://mlsanity.com/paper/1705.10444/) (2017)
- [Self-training with progressive augmentation for unsupervised cross-domain person re-identification](https://mlsanity.com/paper/1907.13315/) (2019)
- [Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/1708.08062/) (2017)
- [Global Distance-distributions Separation for Unsupervised Person Re-identification](https://mlsanity.com/paper/2006.00752/) (2020)

## Abstract (arXiv)

Person re-identification (re-ID) has received great success with the supervised learning methods. However, the task of unsupervised cross-domain re-ID is still challenging. In this paper, we propose a Hard Samples Rectification (HSR) learning scheme which resolves the weakness of original clustering-based methods being vulnerable to the hard positive and negative samples in the target unlabelled dataset. Our HSR contains two parts, an inter-camera mining method that helps recognize a person under different views (hard positive) and a part-based homogeneity technique that makes the model discriminate different persons but with similar appearance (hard negative). By rectifying those two hard cases, the re-ID model can learn effectively and achieve promising results on two large-scale benchmarks.