Redundancy Removal Adversarial Active Learning Based on Norm Online Uncertainty Indicator

Active learning aims to select the most valuable unlabelled samples for annotation. In this paper, we propose a redundancy removal adversarial active learning (RRAAL) method based on norm online uncertainty indicator, which selects samples based on their distribution, uncertainty, and redundancy. RR...

Descripción completa

Detalles Bibliográficos
Autores principales: Guo, Jifeng, Pang, Zhiqi, Sun, Wenbo, Li, Shi, Chen, Yu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2021
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8578688/
https://www.ncbi.nlm.nih.gov/pubmed/34777493
http://dx.doi.org/10.1155/2021/4752568

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8578688/
https://www.ncbi.nlm.nih.gov/pubmed/34777493
http://dx.doi.org/10.1155/2021/4752568

Ejemplares similares