Article

Emergence of Visual Center-Periphery Spatial Organization in Deep Convolutional Neural Networks

2020-02-20

Abstract excerpt

Research at the intersection of computer vision and neuroscience has revealed hierarchical correspondence between layers of deep convolutional neural networks (DCNNs) and cascade of regions along human ventral visual cortex. Recently, studies have uncovered emergence of human interpretable concepts within DCNNs layers trained to identify visual objects and scenes. Here, we asked whether an artificial neural networ...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 24a43822-1394-581d-8acf-e08857c18e1d
DOI: 10.1101/2020.02.19.956748

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Emergence of Visual Center-Periphery Spatial Organization in Deep Convolutional Neural NetworksDOI 10.1101/2020.02.19.956748Read

The representational hierarchy in human and artificial visual systems in the presence of object-scene regularitiesSemantic proximity Read

Hierarchical Emergence Profiles of Human-Derived Dimensions are a Fundamental Property of Deep Neural NetworksSemantic proximity Read

Similarity judgments and cortical visual responses reflect different properties of object and scene categories in naturalistic imagesSemantic proximity Read

A single computational objective can produce specialization of streams in visual cortexSemantic proximity Read

Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain ActivitySemantic proximity Read

Divergent specializations for motion-driven representations in higher lateral and dorsal visual areasSemantic proximity Read

Distributed network flows generate localized category selectivity in human visual cortexSemantic proximity Read

Self-supervised learning yields representational signatures of category-selective cortexSemantic proximity Read

Unravelling Representations in Scene-selective Brain Regions Using Scene Parsing Deep Neural NetworksSemantic proximity Read

High-performing neural network models of visual cortex benefit from high latent dimensionalitySemantic proximity Read

A connectivity-constrained computational account of topographic organization in primate high-level visual cortexSemantic proximity Read

Recent advances in understanding object recognition in the human brain: deep neural networks, temporal dynamics, and contextSemantic proximity Read