# Hard-Aware Point-to-Set Deep Metric for Person Re-identification

arXiv: https://arxiv.org/abs/1807.11206 · HTML: https://mlsanity.com/paper/1807.11206/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2018.

## Built on by (most cited first, 12 of 12)

- [Feature Completion for Occluded Person Re-Identification](https://mlsanity.com/paper/2106.12733/) (2021)
- [Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning](https://mlsanity.com/paper/2103.15454/) (2021)
- [Attributable Visual Similarity Learning](https://mlsanity.com/paper/2203.14932/) (2022)
- [On permutation-invariant neural networks](https://mlsanity.com/paper/2403.17410/) (2024)
- [Adaptive Hierarchical Similarity Metric Learning with Noisy Labels](https://mlsanity.com/paper/2111.00006/) (2021)
- [Sampling Agnostic Feature Representation for Long-Term Person Re-identification](https://mlsanity.com/paper/2209.09574/) (2022)
- [A Brief Survey on Person Recognition at a Distance](https://mlsanity.com/paper/2212.08969/) (2022)
- [Rethinking Deep Contrastive Learning with Embedding Memory](https://mlsanity.com/paper/2103.14003/) (2021)
- [Denoising Multi-Similarity Formulation: A Self-paced Curriculum-Driven Approach for Robust Metric Learning](https://mlsanity.com/paper/2211.11751/) (2022)
- [SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts](https://mlsanity.com/paper/2108.12992/) (2021)
- [Construct Informative Triplet with Two-stage Hard-sample Generation](https://mlsanity.com/paper/2112.02259/) (2021)
- [Domain Camera Adaptation and Collaborative Multiple Feature Clustering for Unsupervised Person Re-ID](https://mlsanity.com/paper/2208.08624/) (2022)

## Abstract (arXiv)

Person re-identification (re-ID) is a highly challenging task due to large variations of pose, viewpoint, illumination, and occlusion. Deep metric learning provides a satisfactory solution to person re-ID by training a deep network under supervision of metric loss, e.g., triplet loss. However, the performance of deep metric learning is greatly limited by traditional sampling methods. To solve this problem, we propose a Hard-Aware Point-to-Set (HAP2S) loss with a soft hard-mining scheme. Based on the point-to-set triplet loss framework, the HAP2S loss adaptively assigns greater weights to harder samples. Several advantageous properties are observed when compared with other state-of-the-art loss functions: 1) Accuracy: HAP2S loss consistently achieves higher re-ID accuracies than other alternatives on three large-scale benchmark datasets; 2) Robustness: HAP2S loss is more robust to outliers than other losses; 3) Flexibility: HAP2S loss does not rely on a specific weight function, i.e., different instantiations of HAP2S loss are equally effective. 4) Generality: In addition to person re-ID, we apply the proposed method to generic deep metric learning benchmarks including CUB-200-2011 and Cars196, and also achieve state-of-the-art results.