Joint Visual and Semantic Optimization for zero-shot learning

作者：

Highlights：

• Match the latent representations in a common subspace for concept sharing.

• The orthogonal constraints can avoid degeneracy and remove redundant information.

• The resulting model is solved effectively by a Gauss–Seidel optimization scheme.

• Results on six benchmark data sets validate the effectiveness of the proposed method.

摘要

•Match the latent representations in a common subspace for concept sharing.•The orthogonal constraints can avoid degeneracy and remove redundant information.•The resulting model is solved effectively by a Gauss–Seidel optimization scheme.•Results on six benchmark data sets validate the effectiveness of the proposed method.

论文关键词：Zero-shot learning,Generalized zero-shot learning,Orthogonal projection

论文评审过程：Received 18 October 2020, Revised 7 January 2021, Accepted 10 January 2021, Available online 14 January 2021, Version of Record 20 January 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.106773