2021
DOI: 10.1109/access.2021.3071134
|View full text |Cite
|
Sign up to set email alerts
|

Noise Resistible Network for Unsupervised Domain Adaptation on Person Re-Identification

Abstract: Unsupervised domain adaptation on person re-identification (re-ID), which adapts the model trained on source dataset to the target dataset, has drawn increasing attention over the past few years. It is more practical than the traditional supervised methods when applied in the real-world scenarios since they require a huge number of manual annotations in a specific domain, which is unrealistic and even under personal privacy concerns. Currently, pseudo label-based method is one of the most promising solutions i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 62 publications
0
2
0
Order By: Relevance
“…Dong et al proposed an asymmetric mutual mean-teaching method for unsupervised adaptive person Re-ID, utilizing two clustering approaches to enhance the confidence of clustering pseudo-labels in [40]. Zhang et al presented an unsupervised domain adaptation person Re-ID framework, NRNet [41], utilizing two dual-stream networks to mitigate pseudo label noise.…”
Section: A Cross-domain Person Re-idmentioning
confidence: 99%
“…Dong et al proposed an asymmetric mutual mean-teaching method for unsupervised adaptive person Re-ID, utilizing two clustering approaches to enhance the confidence of clustering pseudo-labels in [40]. Zhang et al presented an unsupervised domain adaptation person Re-ID framework, NRNet [41], utilizing two dual-stream networks to mitigate pseudo label noise.…”
Section: A Cross-domain Person Re-idmentioning
confidence: 99%
“…Chen et al [13] emphasized deep credible metric learning to address the challenges of unsupervised domain adaptation in person re-identification tasks. Zhang et al [14] addressed the challenge of noise in unsupervised domain adaptation for person re-identification, aiming to enhance model robustness and generalization. Zhang et al [15] emphasized unified domain learning techniques for unsupervised person re-identification, aiming to achieve robust performance across diverse datasets and domains.…”
Section: Related Work a Person Re-identificationmentioning
confidence: 99%