Robust deep learning object recognition models rely on low frequency information in natural images

Machine learning models have difficulty generalizing to data outside of the distribution they were trained on. In particular, vision models are usually vulnerable to adversarial attacks or common corruptions, to which the human visual system is robust. Recent studies have found that regularizing mac...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Zhe, Ortega Caro, Josue, Rusak, Evgenia, Brendel, Wieland, Bethge, Matthias, Anselmi, Fabio, Patel, Ankit B., Tolias, Andreas S., Pitkow, Xaq
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10079058/
https://www.ncbi.nlm.nih.gov/pubmed/36972288
http://dx.doi.org/10.1371/journal.pcbi.1010932

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10079058/
https://www.ncbi.nlm.nih.gov/pubmed/36972288
http://dx.doi.org/10.1371/journal.pcbi.1010932

Ejemplares similares