Detecting failure modes in image reconstructions with interval neural network uncertainty

PURPOSE: The quantitative detection of failure modes is important for making deep neural networks reliable and usable at scale. We consider three examples for common failure modes in image reconstruction and demonstrate the potential of uncertainty quantification as a fine-grained alarm system. METH...

Descripción completa

Detalles Bibliográficos
Autores principales: Oala, Luis, Heiß, Cosmas, Macdonald, Jan, März, Maximilian, Kutyniok, Gitta, Samek, Wojciech
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2021
Materias:
Original Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8616888/
https://www.ncbi.nlm.nih.gov/pubmed/34480723
http://dx.doi.org/10.1007/s11548-021-02482-2

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8616888/
https://www.ncbi.nlm.nih.gov/pubmed/34480723
http://dx.doi.org/10.1007/s11548-021-02482-2

Ejemplares similares