Cargando…
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...
Autores principales: | Guo, Jifeng, Pang, Zhiqi, Sun, Wenbo, Li, Shi, Chen, Yu |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2021
|
Materias: | |
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 |
Ejemplares similares
-
Machine Learning Uncertainties with Adversarial Neural Networks
por: Galler, Peter
Publicado: (2019) -
Machine learning uncertainties with adversarial neural networks
por: Englert, Christoph, et al.
Publicado: (2019) -
Robust adversarial uncertainty quantification for deep learning fine-tuning
por: Ahmed, Usman, et al.
Publicado: (2023) -
Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples
por: Tuna, Omer Faruk, et al.
Publicado: (2022) -
Wasserstein Uncertainty Estimation for Adversarial Domain Matching
por: Wang, Rui, et al.
Publicado: (2022)