@article{Liu2024, 
author = {Fangyi Liu and Mang Ye and Bo Du},
title = {Learning a generalizable re-identification model from unlabelled data with domain-agnostic expert},
year = {2024},
journal = {Visual Intelligence},
volume = {2},
pages = {28},
keywords = {Domain generalization (DG), Unlabeled source domains, Label space inconsistencies, Domain-agnostic expert (DaE)},
url = {https://www.sciopen.com/article/10.1007/s44267-024-00062-x},
doi = {10.1007/s44267-024-00062-x},
abstract = {In response to real-world scenarios, the domain generalization (DG) problem has spurred considerable research in person re-identification (ReID). This challenge arises when the target domain, which is significantly different from the source domains, remains unknown. However, the performance of current DG ReID relies heavily on labor-intensive source domain annotations. Considering the potential of unlabeled data, we investigate unsupervised domain generalization (UDG) in ReID. Our goal is to create a model that can generalize from unlabeled source domains to semantically retrieve images in an unseen target domain. To address this, we propose a new approach that trains a domain-agnostic expert (DaE) for unsupervised domain-generalizable person ReID. This involves independently training multiple experts to account for label space inconsistencies between source domains. At the same time, the DaE captures domain-generalizable information for testing. Our experiments demonstrate the effectiveness of this method for learning generalizable features under the UDG setting. The results demonstrate the superiority of our method over state-of-the-art techniques. We will make our code and models available for public use.}
}