Qian Wang qian.wang@durham.ac.uk
Academic Visitor
Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation
Wang, Qian; Meng, Fanlin; Breckon, Toby P.
Authors
Fanlin Meng
Professor Toby Breckon toby.breckon@durham.ac.uk
Professor
Abstract
Domain adaptation solves image classification problems in the target domain by taking advantage of the labelled source data and unlabelled target data. Usually, the source and target domains share the same set of classes. As a special case, Open-Set Domain Adaptation (OSDA) assumes there exist additional classes in the target domain but are not present in the source domain. To solve such a domain adaptation problem, our proposed method learns discriminative common subspaces for the source and target domains using a novel Open-Set Locality Preserving Projection (OSLPP) algorithm. The source and target domain data are aligned in the learned common spaces class-wise. To handle the open-set classification problem, our method progressively selects target samples to be pseudo-labelled as known classes, rejects the outliers if they are detected as unknown classes, and leaves the remaining target samples as uncertain. The common subspace learning algorithm OSLPP simultaneously aligns the labelled source data and pseudo-labelled target data from known classes and pushes the rejected target data away from the known classes. The common subspace learning and the pseudo-labelled sample selection/rejection facilitate each other in an iterative learning framework and achieve state-of-the-art performance on four benchmark datasets Office-31, Office-Home, VisDA17 and Syn2Real-O with the average HOS of 87.6%, 67.0%, 76.1% and 65.6% respectively.
Citation
Wang, Q., Meng, F., & Breckon, T. P. (2024). Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation. IEEE Transactions on Artificial Intelligence, https://doi.org/10.1109/TAI.2024.3379940
Journal Article Type | Article |
---|---|
Acceptance Date | Mar 17, 2024 |
Online Publication Date | Mar 25, 2024 |
Publication Date | Mar 25, 2024 |
Deposit Date | Mar 26, 2024 |
Publicly Available Date | Mar 27, 2024 |
Journal | IEEE Transactions on Artificial Intelligence |
Electronic ISSN | 2691-4581 |
Publisher | Institute of Electrical and Electronics Engineers |
Peer Reviewed | Peer Reviewed |
DOI | https://doi.org/10.1109/TAI.2024.3379940 |
Keywords | domain adaptation, classification, pseudo-labelling |
Public URL | https://durham-repository.worktribe.com/output/2347522 |
Files
Accepted Journal Article
(2.5 Mb)
PDF
Licence
http://creativecommons.org/licenses/by/4.0/
Copyright Statement
This accepted manuscript is licensed under the Creative Commons Attribution 4.0 licence. https://creativecommons.org/licenses/by/4.0/
You might also like
On Fine-tuned Deep Features for Unsupervised Domain Adaptation
(2023)
Presentation / Conference Contribution
Multi-Class 3D Object Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery
(2021)
Presentation / Conference Contribution
Source Class Selection with Label Propagation for Partial Domain Adaptation
(2021)
Presentation / Conference Contribution
A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks
(2019)
Presentation / Conference Contribution
Unifying Unsupervised Domain Adaptation and Zero-Shot Visual Recognition
(2019)
Presentation / Conference Contribution
Downloadable Citations
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search