Pseudo Distribution on Unseen Classes for Generalized Zero Shot Learning

Zhang, Haofeng; Liu, Jingren; Yao, Yazhou; Long, Yang

Abstract

Although Zero Shot Learning (ZSL) has attracted more and more attention due to its powerful ability of recognizing new objects without retraining, it has a serious drawback that it only focuses on unseen classes during prediction. To solve this issue, Generalized ZSL (GZSL) extends the search range to both seen and unseen classes, which makes it a more realistic and challenging task. Conventional methods on GZSL often suffer from the domain shift problem on seen classes because they have only seen data for training. Deep Calibration Network (DCN) tries to minimize the entropy of assigning seen data to unseen classes to balance the training on both seen and unseen classes. However, there are still two problems for DCN, one is the hubness problem and another is the lack of training guidance. In this paper, to solve the two problems, we propose a novel method called PSeudo Distribution (PSD), which exploits the attribute similarity between seen classes and unseen classes as the training guidance to assign the seen data to unseen classes. In addition, the attribute similarity is also compressed to one-hot vector to further encourage the certainty of the model. Besides, the visual space is utilized as the embedding space, which can well settle the hubness problem. Extensive experiments are conducted on four popular datasets, and the results show the superiority of the proposed method.

Citation

Zhang, H., Liu, J., Yao, Y., & Long, Y. (2020). Pseudo Distribution on Unseen Classes for Generalized Zero Shot Learning. Pattern Recognition Letters, 135, 451-458. https://doi.org/10.1016/j.patrec.2020.05.021

• Journal Article Type: Article
• Acceptance Date: May 18, 2020
• Online Publication Date: May 21, 2020
• Publication Date: Jul 31, 2020
• Deposit Date: May 22, 2020
• Publicly Available Date: May 21, 2021
• Journal: Pattern Recognition Letters
• Print ISSN: 0167-8655
• Electronic ISSN: 1872-7344
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 135
• Pages: 451-458
• DOI: https://doi.org/10.1016/j.patrec.2020.05.021
• Public URL: https://durham-repository.worktribe.com/output/1263862