Article

Using drawings and deep neural networks to characterize the building blocks of human visual similarity

2023-02-07

Abstract excerpt

<p>Early in life and without special training, human beings discern resemblance between abstract visual stimuli such as sketch drawings and the real-world objects they represent. We used this capacity for visual abstraction as a tool for evaluating deep neural networks (DNNs) as models of human visual perception. Contrasting 5 contemporary DNNs, we evaluated how well each explains human similarity judgements among...

Topics

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

Identifiers and source

Literature Corpus work: 78a1f97a-eeb6-51dd-bc6d-056e765d05fe
DOI: 10.31234/osf.io/jmg7d

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Using drawings and deep neural networks to characterize the building blocks of human visual similarityDOI 10.31234/osf.io/jmg7dRead

From photos to sketches - how humans and deep neural networks process objects across different levels of visual abstractionSemantic proximity Read

The spatiotemporal neural dynamics of object recognition for natural images and line drawingsSemantic proximity Read

Revealing the multidimensional mental representations of natural objects underlying human similarity judgmentsSemantic proximity Read

Probing Human Categorization of Naturalistic Images by Combining Deep Neural Networks with Cognitive ModelsSemantic proximity Read

A high-throughput approach for the efficient prediction of perceived similarity of natural objectsSemantic proximity Read

Grounding deep neural network predictions of human categorization behavior in understandable functional features: The case of face identitySemantic proximity Read

Teaching deep networks to see shape: Lessons from a simplified visual worldSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read

How do visual and conceptual factors predict the composition of typical scene drawings?Semantic proximity Read

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

Computational reconstruction of mental representations using human behaviorSemantic proximity Read

Deep Problems with Neural Network Models of Human VisionSemantic proximity Read