Contrastive representation learning with noisy pseudo labels for unsupervised person re-identification

Haiming Sun; Shiwei Ma; Yuan Gao; Kaihua Huang

doi:10.1117/12.3014567

8 December 2023 Contrastive representation learning with noisy pseudo labels for unsupervised person re-identification

Haiming Sun, Shiwei Ma, Yuan Gao, Kaihua Huang

Proceedings Volume 12943, International Workshop on Signal Processing and Machine Learning (WSPML 2023); 129430N (2023) https://doi.org/10.1117/12.3014567
Event: International Workshop on Signal Processing and Machine Learning (WSPML 2023), 2023, Hangzhou, ZJ, China

Abstract

Currently, state-of-the-art unsupervised person re-identification(Re-ID) algorithms employ cluster methods to create pseudo labels by grouping unlabeled data to train the model, but it inevitably generates noisy pseudo labels, which limits the performance of unsupervised person Re-ID task. To tackle the above issue, we suggest the contrastive regularization loss function for the model to concentrate on learning the representation information of correct pseudo labels and ignore those of noisy pseudo labels to the maximum extent. Under the guidance of this method, the model training focuses more on the learning of high quality correct pseudo labels and eliminates the negative consequences of noisy pseudo labels on it, thus boosting the efficiency of the unsupervised person Re-ID mission. The proposal is adequately experimented on three person Re-ID benchmark datasets, and the results prove the usefulness of the method and outperform other state-of-the-art approaches.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Haiming Sun, Shiwei Ma, Yuan Gao, and Kaihua Huang "Contrastive representation learning with noisy pseudo labels for unsupervised person re-identification", Proc. SPIE 12943, International Workshop on Signal Processing and Machine Learning (WSPML 2023), 129430N (8 December 2023); https://doi.org/10.1117/12.3014567

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Performance modeling

Feature extraction

Data modeling

Cameras

Mathematical optimization

Ablation

Show All Keywords

Keywords/Phrases

Search In:

Publication Years