Haofeng Zhang
A plug-in attribute correction module for generalized zero-shot learning
Zhang, Haofeng; Bai, Haoyue; Long, Yang; Liu, Li; Shao, Ling
Abstract
While Zero Shot Learning models can recognize new classes without training examples, they often fails to incorporate both seen and unseen classes together at the test time, which is known as the Generalized Zero-shot Learning (GZSL) problem. This paper identifies a bottleneck issue when attributes are not well-defined, reliable, inaccurate in quantitative representations, or suffering from the visual-semantic discrepancy. We propose a Generic Plug-in Attribute Correction (GPAC) module which can effectively accommodate conventional ZSL in GZSL tasks. Different from existing embedding-based approaches which often lose the favor of transparency in attributes, our key challenge is to fully preserve the original meaning of the attributes and make it complementary and interpretable to upgrade existing ZSL models. To this end, we propose a novel nonnegative constraint with iterative Stochastic Gradient Descent toolbox to effectively fit our GPAC module into previous ZSL models. Extensive experiments on five popular datasets show that our method can effectively correct attributes and make conventional ZSL can achieve state-of-the-art performance on GZSL tasks. It is also a good practice for future models when incorporating prior human knowledge.
Journal Article Type | Article |
---|---|
Acceptance Date | Nov 25, 2020 |
Online Publication Date | Dec 5, 2020 |
Publication Date | 2021-04 |
Deposit Date | May 26, 2021 |
Publicly Available Date | Dec 5, 2022 |
Journal | Pattern Recognition |
Print ISSN | 0031-3203 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 112 |
Article Number | 107767 |
DOI | https://doi.org/10.1016/j.patcog.2020.107767 |
Public URL | https://durham-repository.worktribe.com/output/1247588 |
Files
Accepted Journal Article
(1.1 Mb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by-nc-nd/4.0/
Copyright Statement
© 2021 This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
You might also like
Improving Health Mention Classification through Emphasising Literal Meanings: a Study Towards Diversity and Generalisation for Public Health Surveillance
(2023)
Presentation / Conference Contribution
Towards light-weight annotations: Fuzzy interpolative reasoning for zero-shot image classification
(2018)
Presentation / Conference Contribution
Towards affordable semantic searching: Zero-shot retrieval via dominant attributes
(2018)
Presentation / Conference Contribution
Attribute embedding with visual-semantic ambiguity removal for zero-shot learning
(2016)
Presentation / Conference Contribution
A General Transductive Regularizer for Zero-Shot Learning
(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