1. [Publications](/publications)
2. Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
 
 # Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

  ![](/sites/default/files/styles/wide/public/publications/dg-net%2B%2B.png?itok=_pXMXc8a)

 Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps. Recently, there has been a growing interest in using unsupervised domain adaptation to address this scalability issue. Existing methods typically conduct adaptation on the representation space that contains both id-related and id-unrelated factors, thus inevitably undermining the adaptation efficacy of id-related features. In this paper, we seek to improve adaptation by purifying the representation space to be adapted. To this end, we propose a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id-related feature space exclusively. Our model involves a disentangling module that encodes cross-domain images into a shared appearance space and two separate structure spaces, and an adaptation module that performs adversarial alignment and self-training on the shared appearance space. The two modules are co-designed to be mutually beneficial. Extensive experiments demonstrate that the proposed joint learning framework outperforms the state-of-the-art methods by clear margins.



 ## Authors



Yang Zou (CMU)

Xiaodong Yang (QCraft)

[Zhiding Yu](/person/zhiding-yu)

B. V. K. Vijaya Kumar (CMU)

[Jan Kautz](/person/jan-kautz)

 

 

 ## Publication Date



Monday, August 24, 2020

 

 ## Published in



[European Conference on Computer Vision (ECCV) 2020 (Oral)](https://eccv2020.eu/)

 

 ## Research Area



[Computer Vision](/research-area/computer-vision)

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

 

 

 ## External Links



[Paper (arXiv)](https://arxiv.org/abs/2007.10315)

[Code](https://github.com/NVlabs/DG-Net-PP)