ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning

In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficac...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 12; pp. 9733 - 9740
Main Authors: Yan, Caixia, Chang, Xiaojun, Li, Zhihui, Guan, Weili, Ge, Zongyuan, Zhu, Lei, Zheng, Qinghua
Format: Journal Article
Language:English
Published: New York IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Computer architecture
Datasets
Differentiable architecture search
Generative adversarial networks
Generators
Optimization
Search methods
Source code
Task analysis
Testing
Training
Zero-shot learning
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficacy, however, there is still no guarantee that these hand-crafted models can consistently achieve good performance across diversified datasets or scenarios. Accordingly, in this paper, we turn to neural architecture search (NAS) and make the first attempt to bring NAS techniques into the ZSL realm. Specifically, we propose a differentiable GAN architecture search method over a specifically designed search space for zero-shot learning, referred to as ZeroNAS. Considering the relevance and balance of the generator and discriminator, ZeroNAS jointly searches their architectures in a min-max player game via adversarial training. Extensive experiments conducted on four widely used benchmark datasets demonstrate that ZeroNAS is capable of discovering desirable architectures that perform favorably against state-of-the-art ZSL and generalized zero-shot learning (GZSL) approaches. Source code is at https://github.com/caixiay/ZeroNAS .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2021.3127346