Cargando…
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...
Autores principales: | Baker, Nicholas, Lu, Hongjing, Erlikhman, Gennady, Kellman, Philip J. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6306249/ https://www.ncbi.nlm.nih.gov/pubmed/30532273 http://dx.doi.org/10.1371/journal.pcbi.1006613 |
Ejemplares similares
-
Non-rigid illusory contours and global shape transformations defined by spatiotemporal boundary formation
por: Erlikhman, Gennady, et al.
Publicado: (2014) -
From Flashes to Edges to Objects: Recovery of Local Edge Fragments Initiates Spatiotemporal Boundary Formation
por: Erlikhman, Gennady, et al.
Publicado: (2016) -
Configural relations in humans and deep convolutional neural networks
por: Baker, Nicholas, et al.
Publicado: (2023) -
Transfer of Learning in the Convolutional Neural Networks on Classifying Geometric Shapes Based on Local or Global Invariants
por: Zheng, Yufeng, et al.
Publicado: (2021) -
Transfer Learning with Deep Convolutional Neural Networks for Classifying Cellular Morphological Changes
por: Kensert, Alexander, et al.
Publicado: (2019)