Mr Qian Wang qian.wang@durham.ac.uk
Academic Visitor
Mr Qian Wang qian.wang@durham.ac.uk
Academic Visitor
Professor Toby Breckon toby.breckon@durham.ac.uk
Professor
In traditional unsupervised domain adaptation problems, the target domain is assumed to share the same set of classes as the source domain. In practice, there exist situations where target-domain data are from only a subset of source-domain classes and it is not known which classes the target-domain data belong to since they are unlabeled. This problem has been formulated as Partial Domain Adaptation (PDA) in the literature and is a challenging task due to the negative transfer issue (i.e. source-domain data belonging to the irrelevant classes harm the domain adaptation). We address the PDA problem by detecting the outlier classes in the source domain progressively. As a result, the PDA is boiled down to an easier unsupervised domain adaptation problem which can be solved without the issue of negative transfer. Specifically, we employ the locality preserving projection to learn a latent common subspace in which a label propagation algorithm is used to label the target-domain data. The outlier classes can be detected if no target-domain data are labeled as these classes. We remove the detected outlier classes from the source domain and repeat the process for multiple iterations until convergence. Experimental results on commonly used datasets Office31 and Office-Home demonstrate our proposed method achieves state-of-the-art performance with an average accuracy of 98.1% and 75.4% respectively.
Wang, Q., & Breckon, T. (2021). Source Class Selection with Label Propagation for Partial Domain Adaptation.
Conference Name | International Conference on Image Processing |
---|---|
Conference Location | Anchorage, AK |
Start Date | Sep 19, 2021 |
End Date | Sep 22, 2021 |
Acceptance Date | May 20, 2021 |
Online Publication Date | Aug 23, 2021 |
Publication Date | 2021-09 |
Deposit Date | Jun 24, 2021 |
Publicly Available Date | Sep 23, 2021 |
Publisher | Institute of Electrical and Electronics Engineers |
Related Public URLs | http://breckon.eu/toby/publications/papers/wang21pda.pdf |
Accepted Conference Proceeding
(328 Kb)
PDF
Copyright Statement
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption
(2023)
Conference Proceeding
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
(2023)
Conference Proceeding
Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
(2023)
Conference Proceeding
Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery
(2023)
Conference Proceeding
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
Apache License Version 2.0 (http://www.apache.org/licenses/)
Apache License Version 2.0 (http://www.apache.org/licenses/)
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/)
Advanced Search