Caricamento...

Deep convolutional networks do not classify based on global object shape

Deep convolutional networks (DCNNs) are achieving previously unseen performance in object classification, raising questions about whether DCNNs operate similarly to human vision. In biological vision, shape is arguably the most important cue for recognition. We tested the role of shape information i...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Pubblicato in:PLoS Comput Biol
Autori principali: Baker, Nicholas, Lu, Hongjing, Erlikhman, Gennady, Kellman, Philip J.
Natura: Artigo
Lingua:Inglês
Pubblicazione: Public Library of Science 2018
Soggetti:
Accesso online:https://ncbi.nlm.nih.gov/pmc/articles/PMC6306249/
https://ncbi.nlm.nih.gov/pubmed/30532273
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1371/journal.pcbi.1006613
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne! !