Residual-Prototype Generating Network for Generalized Zero-Shot Learning

Zeqing Zhang, Xiaofan Li, Tai Ma, Zuodong Gao, Cuihua Li and Weiwei Lin ()
Additional contact information
Zeqing Zhang: School of Earth Sciences and Engineering, West Yunnan University of Applied Sciences, Dali 671000, China
Xiaofan Li: School of Informatics, Xiamen University, Xiamen 361000, China
Tai Ma: School of Earth Sciences and Engineering, West Yunnan University of Applied Sciences, Dali 671000, China
Zuodong Gao: School of Informatics, Xiamen University, Xiamen 361000, China
Cuihua Li: School of Informatics, Xiamen University, Xiamen 361000, China
Weiwei Lin: School of Big Data and Artificial Intelligence, Fujian Polytechnic Normal University, Fuqing 350300, China

Mathematics, 2022, vol. 10, issue 19, 1-13

Abstract: Conventional zero-shot learning aims to train a classifier on a training set (seen classes) to recognize instances of novel classes (unseen classes) by class-level semantic attributes. In generalized zero-shot learning (GZSL), the classifier needs to recognize both seen and unseen classes, which is a problem of extreme data imbalance. To solve this problem, feature generative methods have been proposed to make up for the lack of unseen classes. Current generative methods use class semantic attributes as the cues for synthetic visual features, which can be considered mapping of the semantic attribute to visual features. However, this mapping cannot effectively transfer knowledge learned from seen classes to unseen classes because the information in the semantic attributes and the information in visual features are asymmetric: semantic attributes contain key category description information, while visual features consist of visual information that cannot be represented by semantics. To this end, we propose a residual-prototype-generating network (RPGN) for GZSL that extracts the residual visual features from original visual features by an encoder–decoder and synthesizes the prototype visual features associated with semantic attributes by a disentangle regressor. Experimental results show that the proposed method achieves competitive results on four GZSL benchmark datasets with significant gains.

Keywords: deep learning; object recognition; generalized zero-shot learning; generative adversarial network (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/19/3587/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/19/3587/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:19:p:3587-:d:931181

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().