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:

Deep transductive network for generalized zero shot learning.

Zhang, Haofeng and Liu, Li and Long, Yang and Zhang, Zheng and Shao, Ling (2020) 'Deep transductive network for generalized zero shot learning.', Pattern recognition., 105 . p. 107370.


Zero Shot Learning (ZSL) aims to learn projective functions on labeled seen data and transfer the learned functions to unseen classes by discovering their relationship with semantic embeddings. However, the mapping process often suffers from the domain shift problem caused by only using the labeled seen data. In this paper, we propose a novel explainable Deep Transductive Network (DTN) for the task of Generalized ZSL (GZSL) by training on both labeled seen data and unlabeled unseen data, with subsequent testing on both seen classes and unseen classes. The proposed network exploits a KL Divergence constraint to iteratively refine the probability of classifying unlabeled instances by learning from their high confidence assignments with the assistance of an auxiliary target distribution. Besides, to avoid the meaningless ascription assumption of unseen data on GZSL, we also propose an experimental paradigm by splitting the unseen data into two equivalent parts for training and testing respectively. Extensive experiments and detailed analysis demonstrate that our DTN can efficiently handle the problems and achieve the state-of-the-art performance on four popular datasets.

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:10 April 2020
Date deposited:30 April 2020
Date of first online publication:16 April 2020
Date first made open access:16 April 2021

Save or Share this output

Look up in GoogleScholar