A Distinguishable Pseudo-Feature Synthesis Method for Generalized Zero-Shot Learning

Generalized zero-shot learning (GZSL) aims to classify seen classes and unseen classes that are disjoint simultaneously. Hybrid approaches based on pseudo-feature synthesis are currently the most popular among GZSL methods. However, they suffer from problems of negative transfer and low-quality clas...

Descripción completa

Detalles Bibliográficos
Autores principales: Jia, Yunpeng, Ye, Xiufen, Liu, Yusong, Xing, Huiming, Guo, Shuxiang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9726268/
https://www.ncbi.nlm.nih.gov/pubmed/36483289
http://dx.doi.org/10.1155/2022/6220501

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9726268/
https://www.ncbi.nlm.nih.gov/pubmed/36483289
http://dx.doi.org/10.1155/2022/6220501

Ejemplares similares