Miao, Y., Deng, J., Ding, G. et al. (1 more author) (2024) Confidence-guided centroids for unsupervised person re-identification. IEEE Transactions on Information Forensics and Security, 19. pp. 6471-6483. ISSN 1556-6013
Abstract
Unsupervised person re-identification (ReID) aims to train a feature extractor for identity retrieval without exploiting identity labels. Due to the blind trust in imperfect clustering results, the learning is inevitably misled by unreliable pseudo labels. Albeit the pseudo label refinement has been investigated by previous works, they generally leverage auxiliary information such as camera IDs and body part predictions. This work explores the internal characteristics of clusters to refine pseudo labels. To this end, Confidence-Guided Centroids (CGC) are proposed to provide reliable cluster-wise prototypes for feature learning. Since samples with high confidence are exclusively involved in the formation of centroids, the identity information of low-confidence samples, i.e . boundary samples, are NOT likely to contribute to the corresponding centroid. Given the new centroids, the current learning scheme, where samples are forced to learn from their assigned centroids solely, is unwise. To remedy the situation, we propose to use Confidence-Guided pseudo Label (CGL), which enables samples to approach not only the originally assigned centroid but also other centroids that are potentially embedded with their identity information. Empowered by confidence-guided centroids and labels, our method yields comparable performance with, or even outperforms, state-of-the-art pseudo label refinement works that largely leverage auxiliary information.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 The Authors. Except as otherwise noted, this author-accepted version of a journal article published in IEEE Transactions on Information Forensics and Security is made available via the University of Sheffield Research Publications and Copyright Policy under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ |
Keywords: | Person Re-identification; Unsupervised Learning; Centroid; Visual Surveillance |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 17 Jun 2024 10:59 |
Last Modified: | 20 Nov 2024 15:52 |
Status: | Published |
Publisher: | Institute of Electrical and Electronics Engineers |
Refereed: | Yes |
Identification Number: | 10.1109/TIFS.2024.3414310 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:213456 |