Dual Distribution Alignment Network for Generalizable Person Re-Identification

Authors

  • Peixian Chen Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University
  • Pingyang Dai Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University
  • Jianzhuang Liu Noah's Ark Lab, Huawei Tech
  • Feng Zheng Department of Computer Science and Engineering, Southern University of Science and Technology
  • Mingliang Xu School of Information Engineering, Zhengzhou University
  • Qi Tian Cloud & AI, Huawei Tech
  • Rongrong Ji Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University Institute of Artificial Intelligence, Xiamen University

Keywords:

Image and Video Retrieval

Abstract

Domain generalization (DG) offers a preferable real-world setting for Person Re-Identification (Re-ID), which trains a model using multiple source domain datasets and expects it to perform well in an unseen target domain without any model updating. Unfortunately, most DG approaches are designed explicitly for classification tasks, which fundamentally differs from the retrieval task Re-ID. Moreover, existing applications of DG in Re-ID cannot correctly handle the massive variation among Re-ID datasets. In this paper, we identify two fundamental challenges in DG for Person Re-ID: domain-wise variations and identity-wise similarities. To this end, we propose an end-to-end Dual Distribution Alignment Network (DDAN) to learn domain-invariant features with dual-level constraints: the domain-wise adversarial feature learning and the identity-wise similarity enhancement. These constraints effectively reduce the domain-shift among multiple source domains further while agreeing to real-world scenarios. We evaluate our method in a large-scale DG Re-ID benchmark and compare it with various cutting-edge DG approaches. Quantitative results show that DDAN achieves state-of-the-art performance.

Downloads

Published

2021-05-18

How to Cite

Chen, P., Dai, P., Liu, J., Zheng, F., Xu, M., Tian, Q., & Ji, R. (2021). Dual Distribution Alignment Network for Generalizable Person Re-Identification. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1054-1062. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16190

Issue

Section

AAAI Technical Track on Computer Vision I