Cargando…

Use of superordinate labels yields more robust and human-like visual representations in convolutional neural networks

Human visual recognition is outstandingly robust. People can recognize thousands of object classes in the blink of an eye (50–200 ms) even when the objects vary in position, scale, viewpoint, and illumination. What aspects of human category learning facilitate the extraction of invariant visual feat...

Descripción completa

Detalles Bibliográficos
Autores principales: Ahn, Seoyoung, Zelinsky, Gregory J., Lupyan, Gary
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8727315/
https://www.ncbi.nlm.nih.gov/pubmed/34967860
http://dx.doi.org/10.1167/jov.21.13.13