Cookies

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:

Modality independent adversarial network for generalized zero shot image classification

Zhang, Haofeng and Wang, Yinduo and Long, Yang and Yang, Longzhi and Shao, Ling (2021) 'Modality independent adversarial network for generalized zero shot image classification.', Neural Networks, 134 . pp. 11-22.

Abstract

Zero Shot Learning (ZSL) aims to classify images of unseen target classes by transferring knowledge from source classes through semantic embeddings. The core of ZSL research is to embed both visual representation of object instance and semantic description of object class into a joint latent space and learn cross-modal (visual and semantic) latent representations. However, the learned representations by existing efforts often fail to fully capture the underlying cross-modal semantic consistency, and some of the representations are very similar and less discriminative. To circumvent these issues, in this paper, we propose a novel deep framework, called Modality Independent Adversarial Network (MIANet) for Generalized Zero Shot Learning (GZSL), which is an end-to-end deep architecture with three submodules. First, both visual feature and semantic description are embedded into a latent hyper-spherical space, where two orthogonal constraints are employed to ensure the learned latent representations discriminative. Second, a modality adversarial submodule is employed to make the latent representations independent of modalities to make the shared representations grab more cross-modal high-level semantic information during training. Third, a cross reconstruction submodule is proposed to reconstruct latent representations into the counterparts instead of themselves to make them capture more modality irrelevant information. Comprehensive experiments on five widely used benchmark datasets are conducted on both GZSL and standard ZSL settings, and the results show the effectiveness of our proposed method.

Item Type:Article
Full text:(AM) Accepted Manuscript
Available under License - Creative Commons Attribution Non-commercial No Derivatives 4.0.
Download PDF
(3199Kb)
Status:Peer-reviewed
Publisher Web site:https://doi.org/10.1016/j.neunet.2020.11.007
Publisher statement:© 2021 This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
Date accepted:15 November 2020
Date deposited:26 May 2021
Date of first online publication:21 November 2020
Date first made open access:21 November 2021

Save or Share this output

Export:
Export
Look up in GoogleScholar