Convolutional prototype learning for zero-shot recognition

作者：

Highlights：

• A simple yet effective convolutional prototype learning (CPL) framework is proposed for zero-shot recognition task.

• CPL can facilitate the effective transferring of the learned knowledge from the source domain to the unseen target domain.

• The generated prototypes are more discriminative due to the joint embedding of both the attribute and class level semantic.

• Compared with some state-of-the-art ZSL methods, our CPL shows competitive results under various ZSL settings.

摘要

•A simple yet effective convolutional prototype learning (CPL) framework is proposed for zero-shot recognition task.•CPL can facilitate the effective transferring of the learned knowledge from the source domain to the unseen target domain.•The generated prototypes are more discriminative due to the joint embedding of both the attribute and class level semantic.•Compared with some state-of-the-art ZSL methods, our CPL shows competitive results under various ZSL settings.

论文关键词：Zero-shot recognition,Prototype learning,Image recognition,Deep learning

论文评审过程：Received 10 February 2020, Revised 1 April 2020, Accepted 10 April 2020, Available online 21 April 2020, Version of Record 4 May 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2020.103924