# Cross-Entropy Adversarial View Adaptation for Person Re-identification

arXiv: https://arxiv.org/abs/1904.01755 · HTML: https://mlsanity.com/paper/1904.01755/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

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

- [SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2102.12137/) (2021)
- [Asymmetric Cross-Scale Alignment for Text-Based Person Search](https://mlsanity.com/paper/2212.11958/) (2022)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Deep Learning-based Occluded Person Re-identification: A Survey](https://mlsanity.com/paper/2207.14452/) (2022)
- [Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2207.13035/) (2022)
- [Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers](https://mlsanity.com/paper/2306.03492/) (2023)
- [A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation](https://mlsanity.com/paper/2402.19330/) (2024)
- [Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification](https://mlsanity.com/paper/2207.13037/) (2022)
- [Generalizable Metric Network for Cross-domain Person Re-identification](https://mlsanity.com/paper/2306.11991/) (2023)
- [Complete Solution for Vehicle Re-ID in Surround-view Camera System](https://mlsanity.com/paper/2212.04126/) (2022)
- [Domain-adaptive Person Re-identification without Cross-camera Paired Samples](https://mlsanity.com/paper/2307.06533/) (2023)
- [FedCVU: Federated Learning for Cross-View Video Understanding](https://mlsanity.com/paper/2603.21647/) (2026)

## Abstract (arXiv)

Person re-identification (re-ID) is a task of matching pedestrians under disjoint camera views. To recognise paired snapshots, it has to cope with large cross-view variations caused by the camera view shift. Supervised deep neural networks are effective in producing a set of non-linear projections that can transform cross-view images into a common feature space. However, they typically impose a symmetric architecture, yielding the network ill-conditioned on its optimisation. In this paper, we learn view-invariant subspace for person re-ID, and its corresponding similarity metric using an adversarial view adaptation approach. The main contribution is to learn coupled asymmetric mappings regarding view characteristics which are adversarially trained to address the view discrepancy by optimising the cross-entropy view confusion objective. To determine the similarity value, the network is empowered with a similarity discriminator to promote features that are highly discriminant in distinguishing positive and negative pairs. The other contribution includes an adaptive weighing on the most difficult samples to address the imbalance of within/between-identity pairs. Our approach achieves notable improved performance in comparison to state-of-the-arts on benchmark datasets.