Similarity-preserving Image-image Domain Adaptation for Person Re-identification

TL;DR

This paper introduces a similarity-preserving generative adversarial network framework for unsupervised domain adaptation in person re-identification, effectively maintaining identity information during image translation to improve re-ID performance.

Contribution

It proposes SPGAN and eSPGAN, novel methods that preserve identity similarity during image translation for domain adaptation in person re-ID, with eSPGAN enabling end-to-end training.

Findings

SPGAN and eSPGAN effectively preserve identity information in translated images.

The methods achieve state-of-the-art results on large-scale re-ID datasets.

End-to-end training of eSPGAN improves domain adaptation performance.

Abstract

This article studies the domain adaptation problem in person re-identification (re-ID) under a "learning via translation" framework, consisting of two components, 1) translating the labeled images from the source to the target domain in an unsupervised manner, 2) learning a re-ID model using the translated images. The objective is to preserve the underlying human identity information after image translation, so that translated images with labels are effective for feature learning on the target domain. To this end, we propose a similarity preserving generative adversarial network (SPGAN) and its end-to-end trainable version, eSPGAN. Both aiming at similarity preserving, SPGAN enforces this property by heuristic constraints, while eSPGAN does so by optimally facilitating the re-ID model learning. More specifically, SPGAN separately undertakes the two components in the "learning via translation" framework. It first preserves two types of unsupervised similarity, namely, self-similarity of an image before and after translation, and domain-dissimilarity of a translated source image and a target image. It then learns a re-ID model using existing networks. In comparison, eSPGAN seamlessly integrates image translation and re-ID model learning. During the end-to-end training of eSPGAN, re-ID learning guides image translation to preserve the underlying identity information of an image. Meanwhile, image translation improves re-ID learning by providing identity-preserving training samples of the target domain style. In the experiment, we show that identities of the fake images generated by SPGAN and eSPGAN are well preserved. Based on this, we report the new state-of-the-art domain adaptation results on two large-scale person re-ID datasets.