Abstract
Unsupervised domain adaptation (UDA) aims at adapting the model trained on a labeled source-domain dataset to another target-domain dataset without any annotation. The task of UDA for the open-set person re-identification (re-ID) is even more challenging as the identities (classes) have no overlap between the two domains. Existing UDA methods for person re-ID have the following limitations. 1) Pseudo-label-based methods achieve state-of-the-art performances but ignore the complex relations between two domains' images, along with the valuable source-domain annotations. 2) Domain translation-based methods cannot achieve competitive performances as the domain translation is not properly regularized to generate informative enough training samples that well maintain inter-sample relations. To tackle the above challenges, we propose an end-to-end structured domain adaptation framework that consists of a novel structured domain-translation network and two domain-specific person image encoders. The structured domain-translation network can effectively transform the source-domain images into the target domain while well preserving the original intra- and inter-identity relations. The target-domain encoder could then be trained using both source-to-target translated images with valuable ground-truth labels and target-domain images with pseudo labels. Importantly, the domain-translation network and target-domain encoder are jointly optimized, improving each other towards the overall objective, i.e. to achieve optimal re-ID performances on the target domain. Our proposed framework outperforms state-of-the-art methods on multiple UDA tasks of person re-ID.
Abstract (translated)
URL
https://arxiv.org/abs/2003.06650
