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

06/26/2021
by   Huafeng Li, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 4

research
10/19/2020

Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

Aiming at recognizing images of the same person across distinct camera v...
research
09/20/2019

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Person re-identification (re-ID) aims at recognizing the same person fro...
research
04/02/2019

Camera Adversarial Transfer for Unsupervised Person Re-Identification

Unsupervised person re-identification (Re-ID) methods consist of trainin...
research
05/30/2019

Attention: A Big Surprise for Cross-Domain Person Re-Identification

In this paper, we focus on model generalization and adaptation for cross...
research
09/15/2023

Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval

Person re-identification (re-ID) requires densely distributed cameras. I...
research
08/24/2019

SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification

Cross-domain person re-identification (re-ID) is challenging due to the ...
research
10/15/2019

Learning Generalisable Omni-Scale Representations for Person Re-Identification

An effective person re-identification (re-ID) model should learn feature...

Please sign up or login with your details

Forgot password? Click here to reset