Spectral decoupling for training transferable neural networks in medical imaging

Many neural networks for medical imaging generalize poorly to data unseen during training. Such behavior can be caused by overfitting easy-to-learn features while disregarding other potentially informative features. A recent implicit bias mitigation technique called spectral decoupling provably enco...

Descripción completa

Detalles Bibliográficos
Autores principales: Pohjonen, Joona, Stürenberg, Carolin, Rannikko, Antti, Mirtti, Tuomas, Pitkänen, Esa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8816718/
https://www.ncbi.nlm.nih.gov/pubmed/35146385
http://dx.doi.org/10.1016/j.isci.2022.103767

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8816718/
https://www.ncbi.nlm.nih.gov/pubmed/35146385
http://dx.doi.org/10.1016/j.isci.2022.103767

Ejemplares similares