Triple Verification Network for Generalized Zero-Shot Learning

Zhang, Haofeng; Long, Yang; Guan, Yu; Shao, Ling

Abstract

Conventional zero-shot learning approaches often suffer from severe performance degradation in the generalized zero-shot learning (GZSL) scenario, i.e., to recognize test images that are from both seen and unseen classes. This paper studies the Class-level Over-fitting (CO) and empirically shows its effects to GZSL. We then address ZSL as a triple verification problem and propose a unified optimization of regression and compatibility functions, i.e., two main streams of existing ZSL approaches. The complementary losses mutually regularizes the same model to mitigate the CO problem. Furthermore, we implement a deep extension paradigm to linear models and significantly outperform state-of-the-art methods in both GZSL and ZSL scenarios on the four standard benchmarks.

Citation

Zhang, H., Long, Y., Guan, Y., & Shao, L. (2019). Triple Verification Network for Generalized Zero-Shot Learning. IEEE Transactions on Image Processing, 28(1), 506-517. https://doi.org/10.1109/tip.2018.2869696

• Journal Article Type: Article
• Acceptance Date: Sep 3, 2018
• Online Publication Date: Sep 24, 2018
• Publication Date: 2019-01
• Deposit Date: Aug 31, 2019
• Journal: IEEE Transactions on Image Processing
• Print ISSN: 1057-7149
• Electronic ISSN: 1941-0042
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 28
• Issue: 1
• Pages: 506-517
• DOI: https://doi.org/10.1109/tip.2018.2869696
• Public URL: https://durham-repository.worktribe.com/output/1289236
• Related Public URLs: https://eprint.ncl.ac.uk/251471