Conscious object recognition is a critical brain function, key to making sense of the plethora of visual inputs and guiding adaptive behavior. Yet, the sequence of neural processing underlying conscious object recognition remains unclear. Existing proposals alternatively suggest that conscious object recognition procee...
Ayaka Hachisuka, T. Baumgarten, Dillan Spector et al.· bioRxiv· 0 citations
Summary Deep neural networks (DNNs) are promising computational models for understanding visual object recognition. Yet, whether DNNs use similar visual cues for object recognition as humans do remains unknown. We created an image set that systematically untangles global shape, internal parts, and texture information,...
An image set that systematically untangles global shape, internal parts, and texture information is created, and human recognition behavior against >200 DNNs spanning diverse architectures, training diets, and training objectives is compared, revealing systematic and persistent differences between human and machine vis...
Mugihiko Kato, Biyu J. He· bioRxiv· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
