Your browser doesn't support javascript.
loading
Perceptual Dominance in Brief Presentations of Mixed Images: Human Perception vs. Deep Neural Networks.
Gruber, Liron Z; Haruvi, Aia; Basri, Ronen; Irani, Michal.
Afiliación
  • Gruber LZ; Department of Neurobiology, Weizmann Institute of Science, Rehovot, Israel.
  • Haruvi A; Department of Neurobiology, Weizmann Institute of Science, Rehovot, Israel.
  • Basri R; Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel.
  • Irani M; Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot, Israel.
Front Comput Neurosci ; 12: 57, 2018.
Article en En | MEDLINE | ID: mdl-30087604
Visual perception involves continuously choosing the most prominent inputs while suppressing others. Neuroscientists induce visual competitions in various ways to study why and how the brain makes choices of what to perceive. Recently deep neural networks (DNNs) have been used as models of the ventral stream of the visual system, due to similarities in both accuracy and hierarchy of feature representation. In this study we created non-dynamic visual competitions for humans by briefly presenting mixtures of two images. We then tested feed-forward DNNs with similar mixtures and examined their behavior. We found that both humans and DNNs tend to perceive only one image when presented with a mixture of two. We revealed image parameters which predict this perceptual dominance and compared their predictability for the two visual systems. Our findings can be used to both improve DNNs as models, as well as potentially improve their performance by imitating biological behaviors.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Front Comput Neurosci Año: 2018 Tipo del documento: Article País de afiliación: Israel Pais de publicación: Suiza

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies Idioma: En Revista: Front Comput Neurosci Año: 2018 Tipo del documento: Article País de afiliación: Israel Pais de publicación: Suiza