.png){kind=icon}
Return
Triple Verification Network for Generalized Zero-Shot Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2018.2869696.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 GMT, and ZSL scenarios on the four standard benchmarks.
Keywords:
Generalized zero shot learning
triple verification
orthogonal projection
dual regression
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
View more