Semantics Disentangling for Generalized Zero-Shot Learning
Paper
Paper/Presentation Title | Semantics Disentangling for Generalized Zero-Shot Learning |
---|---|
Presentation Type | Paper |
Authors | Chen, Zhi, Luo, Yadan, Qui, Ruihong, Wang, Sen, Huang, Zi, Li, Jingjing and Zhang, Zheng |
Journal or Proceedings Title | Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
Journal Citation | pp. 8692-8700 |
Number of Pages | 9 |
Year | 2022 |
Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
Place of Publication | United States |
ISBN | 9781665428125 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICCV48922.2021.00859 |
Web Address (URL) of Paper | https://ieeexplore.ieee.org/document/9710280 |
Web Address (URL) of Conference Proceedings | https://ieeexplore.ieee.org/xpl/conhome/9709627/proceeding |
Conference/Event | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) |
Event Details | 2021 IEEE/CVF International Conference on Computer Vision (ICCV) Delivery In person Event Date 10 to end of 17 Oct 2021 Event Location Montreal, Canada |
Abstract | Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training. To bridge the gap between the seen and unseen classes, most GZSL methods attempt to associate the visual features of seen classes with attributes or to generate unseen samples directly. Nevertheless, the visual features used in the prior approaches do not necessarily encode semantically related information that the shared attributes refer to, which degrades the model generalization to unseen classes. To address this issue, in this paper, we propose a novel semantics disentangling framework for the generalized zero-shot learning task (SDGZSL), where the visual features of unseen classes are firstly estimated by a conditional VAE and then factorized into semantic-consistent and semantic-unrelated latent vectors. In particular, a total correlation penalty is applied to guarantee the independence between the two factorized representations, and the semantic consistency of which is measured by the derived relation network. Extensive experiments conducted on four GZSL benchmark datasets have evidenced that the semantic-consistent features disentangled by the proposed SDGZSL are more generalizable in tasks of canonical and generalized zero-shot learning. Our source code is available at https://github.com/uqzhichen/SDGZSL. |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 4602. Artificial intelligence |
Public Notes | Semantics Disentangling for Generalized Zero-Shot Learning |
Byline Affiliations | University of Queensland |
University of Electronic Science and Technology of China, China | |
Harbin Institute of Technology, China |
https://research.usq.edu.au/item/zyx23/semantics-disentangling-for-generalized-zero-shot-learning
19
total views1
total downloads12
views this month0
downloads this month