Guided CNN for generalized zero-shot and open-set recognition using visual and semantic prototypes

作者：

Highlights：

• Decomposing G-ZSL task into an OSR task and a ZSL task while jointly.

• training the models of these two tasks effectively addresses the CO problem which is ubiquitous in most existing G-ZSL methods.

• Introducing the accumulated side information from known classes to OSR to first explore a new generalized open set recognition (G OSR) task.

• A visual and semantic prototypes jointly guided convolutional ne ural net work (VSG CNN) is proposed to fulfill these two tasks (G ZSL and G OSR) in a unified end to end learning framework.

• Extensive experiments on benchmark datasets indicate the validity of our VSG-CNN.

摘要

•Decomposing G-ZSL task into an OSR task and a ZSL task while jointly.•training the models of these two tasks effectively addresses the CO problem which is ubiquitous in most existing G-ZSL methods.•Introducing the accumulated side information from known classes to OSR to first explore a new generalized open set recognition (G OSR) task.•A visual and semantic prototypes jointly guided convolutional ne ural net work (VSG CNN) is proposed to fulfill these two tasks (G ZSL and G OSR) in a unified end to end learning framework.•Extensive experiments on benchmark datasets indicate the validity of our VSG-CNN.

论文关键词：Convolutional prototype learning,Generalized zero-shot Learning,Open set recognition

论文评审过程：Received 14 August 2019, Revised 4 December 2019, Accepted 5 February 2020, Available online 7 February 2020, Version of Record 13 February 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107263