Non-Deep Active Learning for Deep Neural Networks

One way to improve annotation efficiency is active learning. The goal of active learning is to select images from many unlabeled images, where labeling will improve the accuracy of the machine learning model the most. To select the most informative unlabeled images, conventional methods use deep neu...

Descripción completa

Detalles Bibliográficos
Autores principales: Kawano, Yasufumi, Nota, Yoshiki, Mochizuki, Rinpei, Aoki, Yoshimitsu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9319968/
https://www.ncbi.nlm.nih.gov/pubmed/35890924
http://dx.doi.org/10.3390/s22145244

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9319968/
https://www.ncbi.nlm.nih.gov/pubmed/35890924
http://dx.doi.org/10.3390/s22145244

Ejemplares similares