Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

01/29/2023
by   Qiong Wu, et al.
0

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity information by considering multiple homogeneous networks. And take these generated labels to train the model in the target domain. However, these homogeneous networks identify people in approximate subspaces and equally exchange their knowledge with others or their mean net to improve their ability, inevitably limiting the scope of available knowledge and putting them into the same mistake. This paper proposes a Dual-level Asymmetric Mutual Learning method (DAML) to learn discriminative representations from a broader knowledge scope with diverse embedding spaces. Specifically, two heterogeneous networks mutually learn knowledge from asymmetric subspaces through the pseudo label generation in a hard distillation manner. The knowledge transfer between two networks is based on an asymmetric mutual learning manner. The teacher network learns to identify both the target and source domain while adapting to the target domain distribution based on the knowledge of the student. Meanwhile, the student network is trained on the target dataset and employs the ground-truth label through the knowledge of the teacher. Extensive experiments in Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiority of DAML over state-of-the-arts.

READ FULL TEXT

page 1

page 8

research
11/27/2020

Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification

The objective of unsupervised person re-identification (Re-ID) is to lea...
research
03/14/2020

Structured Domain Adaptation for Unsupervised Person Re-identification

Unsupervised domain adaptation (UDA) aims at adapting the model trained ...
research
08/21/2021

Robust Ensembling Network for Unsupervised Domain Adaptation

Recently, in order to address the unsupervised domain adaptation (UDA) p...
research
07/03/2020

Multiple Expert Brainstorming for Domain Adaptive Person Re-identification

Often the best performing deep neural models are ensembles of multiple b...
research
06/11/2020

Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification

Unsupervised domain adaptation (UDA) for person re-identification is cha...
research
07/10/2022

Dual-Correction Adaptation Network for Noisy Knowledge Transfer

Previous unsupervised domain adaptation (UDA) methods aim to promote tar...
research
08/01/2019

Learning to Adapt Invariance in Memory for Person Re-identification

This work considers the problem of unsupervised domain adaptation in per...

Please sign up or login with your details

Forgot password? Click here to reset