# Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation

arXiv: https://arxiv.org/abs/1905.05382 · HTML: https://mlsanity.com/paper/1905.05382/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2019.

## Built on by (most cited first, 11 of 11)

- [Towards Unsupervised Domain Adaptation via Domain-Transformer](https://mlsanity.com/paper/2202.13777/) (2022)
- [Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification](https://mlsanity.com/paper/2106.13929/) (2021)
- [Domain Adaptive Egocentric Person Re-identification](https://mlsanity.com/paper/2103.04870/) (2021)
- [Generalized Label Shift Correction via Minimum Uncertainty Principle: Theory and Algorithm](https://mlsanity.com/paper/2202.13043/) (2022)
- [Adversarial Self-Attack Defense and Spatial-Temporal Relation Mining for Visible-Infrared Video Person Re-Identification](https://mlsanity.com/paper/2307.03903/) (2023)
- [SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss](https://mlsanity.com/paper/2202.09515/) (2022)
- [Maximizing Conditional Independence for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2203.03212/) (2022)
- [Partial Domain Adaptation via Importance Sampling-based Shift Correction](https://mlsanity.com/paper/2507.20191/) (2025)
- [Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning](https://mlsanity.com/paper/2304.12448/) (2023)
- [Person Re-ID through Unsupervised Hypergraph Rank Selection and Fusion](https://mlsanity.com/paper/2304.14321/) (2023)
- [Geometry-Aware Unsupervised Domain Adaptation](https://mlsanity.com/paper/2112.11041/) (2021)

## Abstract (arXiv)

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping labels challenge that source domain and target domain have entirely different persons further increases the re-identification difficulty. In this paper, we propose a novel algorithm to narrow such domain gaps. We derive a camera style adaptation framework to learn the style-based mappings between different camera views, from the target domain to the source domain, and then we can transfer the identity-based distribution from the source domain to the target domain on the camera level. To overcome the non-overlapping labels challenge and guide the person re-identification model to narrow the gap further, an efficient and effective soft-labeling method is proposed to mine the intrinsic local structure of the target domain through building the connection between GAN-translated source domain and the target domain. Experiment results conducted on real benchmark datasets indicate that our method gets state-of-the-art results.