Humans and deep networks largely agree on which kinds of variation make object recognition harder

View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g. 3D rotations). Humans...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Saeed Reza Kheradpisheh, Masoud Ghodrati, Mohammad Ganjtabesh, Timothée Masquelier
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Frontiers Media S.A. 2016-08-01
Edice:	Frontiers in Computational Neuroscience
Témata:	deep networks Rapid Invariant Object Recognition Ventral Stream Models Feed-forward Vision 2D and 3D Object Variations
On-line přístup:	http://journal.frontiersin.org/Journal/10.3389/fncom.2016.00092/full
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!