- Title
- Bidirectional mapping coupled GAN for generalized zero-shot learning
- Creator
- Shermin, Tasfia; Teng, Shyh; Sohel, Ferdous; Murshed, Manzur; Lu, Guojun
- Date
- 2022
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/185903
- Identifier
- vital:16796
- Identifier
-
https://doi.org/10.1109/TIP.2021.3135480
- Identifier
- ISBN:1057-7149 (ISSN)
- Abstract
- Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen classes and preserving the distinction between seen-unseen classes is crucial for GZSL methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining seen-unseen classes distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the concept of the coupled generative adversarial network into a bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining distinctive information of seen-unseen classes in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods. © 1992-2012 IEEE.
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Relation
- IEEE Transactions on Image Processing Vol. 31, no. (2022), p. 721-733
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright © 2021 IEEE
- Rights
- Open Access
- Subject
- 4603 Computer vision and multimedia computation; 4607 Graphics, augmented reality and games; Bidirectional mapping; Generalized zero-shot learning; Generative adversarial networks
- Full Text
- Reviewed
- Hits: 1233
- Visitors: 1242
- Downloads: 133
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE1 | Accepted version | 724 KB | Adobe Acrobat PDF | View Details Download |