Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification

TL;DR

This paper introduces a dual-stream adversarial learning framework for unsupervised person re-identification that effectively disentangles domain-invariant features without image generation, improving cross-domain matching accuracy.

Contribution

The paper proposes a novel dual-stream reciprocal disentanglement learning method that efficiently learns domain-invariant features without relying on image generation techniques.

Findings

Outperforms state-of-the-art methods in unsupervised person Re-ID

Reduces computational complexity by avoiding image generation

Effectively disentangles id-related and id-unrelated features

Abstract

Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera styles, illumination and backgrounds, there exists a large gap between source domain and target domain, introducing a great challenge on cross-domain matching. To tackle this problem, in this paper we propose a novel method named Dual-stream Reciprocal Disentanglement Learning (DRDL), which is quite efficient in learning domain-invariant features. In DRDL, two encoders are first constructed for id-related and id-unrelated feature extractions, which are respectively measured by their associated classifiers. Furthermore, followed by an adversarial learning strategy, both streams reciprocally and positively effect each other, so that the id-related features and id-unrelated features are completely disentangled from a given image, allowing the encoder to be powerful enough to obtain the discriminative but domain-invariant features. In contrast to existing approaches, our proposed method is free from image generation, which not only reduces the computational complexity remarkably, but also removes redundant information from id-related features. Extensive experiments substantiate the superiority of our proposed method compared with the state-of-the-arts. The source code has been released in https://github.com/lhf12278/DRDL.