Details

Autor(en) / Beteiligte

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

Titel

Triple Verification Network for Generalized Zero-Shot Learning

Ist Teil von

• IEEE transactions on image processing, 2019-01, Vol.28 (1), p.506-517

Ort / Verlag

United States: IEEE

Erscheinungsjahr

2019

Quelle

IEEE Xplore Digital Library

Beschreibungen/Notizen

• 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.