Integrated generalized zero-shot learning for fine-grained classification

作者：

Highlights：

• Integrates embedding learning (EL) and feature synthesizing (FS) styles of GZSL.

• New attention module to explore distinctive local features for fine-grained GZSL.

• Novel mutual learning by minimizing losses between EL and adversarial FS.

• New similarity score using mutual information of seen and unseen domain semantics.

• Superior empirical performance on benchmark datasets.

摘要

•Integrates embedding learning (EL) and feature synthesizing (FS) styles of GZSL.•New attention module to explore distinctive local features for fine-grained GZSL.•Novel mutual learning by minimizing losses between EL and adversarial FS.•New similarity score using mutual information of seen and unseen domain semantics.•Superior empirical performance on benchmark datasets.

论文关键词：Generalized zero-shot learning,Fine-grained classification,Dense attention mechanism

论文评审过程：Received 8 February 2021, Revised 29 June 2021, Accepted 11 August 2021, Available online 19 August 2021, Version of Record 26 August 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108246