Publication detailsZhang, Haofeng, Long, Yang, Guan, Yu & Shao, Ling (2019). Triple Verification Network for Generalized Zero-Shot Learning. IEEE Transactions on Image Processing 28(1): 506-517.
- Publication type: Journal Article
- ISSN/ISBN: 1057-7149, 1941-0042
- DOI: 10.1109/TIP.2018.2869696
- Further publication details on publisher web site
- View in another repository - may include full text
Author(s) from Durham
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.