We use cookies to ensure that we give you the best experience on our website. By continuing to browse this repository, you give consent for essential cookies to be used. You can read more about our Privacy and Cookie Policy.

Durham Research Online
You are in:

Learning discriminative domain-invariant prototypes for generalized zero shot learning.

Wang, Yinduo and Zhang, Haofeng and Zhang, Zheng and Long, Yang and Shao, Ling (2020) 'Learning discriminative domain-invariant prototypes for generalized zero shot learning.', Knowledge-based systems., 196 . p. 105796.


Zero-shot learning (ZSL) aims to recognize objects of target classes by transferring knowledge from source classes through the semantic embeddings bridging. However, ZSL focuses the recognition only on unseen classes, which is unreasonable in realistic scenarios. A more reasonable way is to recognize new samples on combined domains, namely Generalized Zero Shot Learning (GZSL). Due to the fact that the source domain and target domain are disjoint and have unrelated classes potentially, ZSL and GZSL often suffer from the problem of projection domain shift. Besides, some semantic embeddings of prototypes are very similar, which makes the recognition less discriminative. To circumvent these issues, in this paper, we propose a novel method, called Learning Discriminative Domain-Invariant Prototypes (DDIP). In DDIP, both target and source domains are combined and projected into a hyper-spherical space, which is automatically learned by a regularized dictionary learning. In addition, an orthogonal constraint is employed to the latent hyper-spherical space to ensure all the class prototypes, including seen classes and unseen classes, to be orthogonal to each other to make them more discriminative. Extensive experiments on four popular benchmark and a large-scale datasets are conducted on both GZSL and standard ZSL settings, and the results show that our DDIP can outperform the state-of-the-art methods.

Item Type:Article
Full text:(AM) Accepted Manuscript
Available under License - Creative Commons Attribution Non-commercial No Derivatives.
Download PDF
Publisher Web site:
Publisher statement:© 2020 This manuscript version is made available under the CC-BY-NC-ND 4.0 license
Date accepted:19 March 2020
Date deposited:26 March 2020
Date of first online publication:24 March 2020
Date first made open access:24 March 2021

Save or Share this output

Look up in GoogleScholar