# Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification

arXiv: https://arxiv.org/abs/1811.11510 · HTML: https://mlsanity.com/paper/1811.11510/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2018.

## Built on by (most cited first, 4 of 4)

- [HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping](https://mlsanity.com/paper/2106.09965/) (2021)
- [DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID](https://mlsanity.com/paper/2411.07205/) (2024)
- [Disentangled Representations for Short-Term and Long-Term Person Re-Identification](https://mlsanity.com/paper/2409.05277/) (2024)
- [A Bidirectional Conversion Network for Cross-Spectral Face Recognition](https://mlsanity.com/paper/2205.01595/) (2022)

## Abstract (arXiv)

Person re-identification is to retrieval pedestrian images from no-overlap camera views detected by pedestrian detectors. Most existing person re-identification (re-ID) models often fail to generalize well from the source domain where the models are trained to a new target domain without labels, because of the bias between the source and target domain. This issue significantly limits the scalability and usability of the models in the real world. Providing a labeled source training set and an unlabeled target training set, the aim of this paper is to improve the generalization ability of re-ID models to the target domain. To this end, we propose an image generative network named identity preserving generative adversarial network (IPGAN). The proposed method has two excellent properties: 1) only a single model is employed to translate the labeled images from the source domain to the target camera domains in an unsupervised manner; 2) The identity information of images from the source domain is preserved before and after translation. Furthermore, we propose IBN-reID model for the person re-identification task. It has better generalization ability than baseline models, especially in the cases without any domain adaptation. The IBN-reID model is trained on the translated images by supervised methods. Experimental results on Market-1501 and DukeMTMC-reID show that the images generated by IPGAN are more suitable for cross-domain person re-identification. Very competitive re-ID accuracy is achieved by our method.