Article

Teaching deep networks to see shape: Lessons from a simplified visual world

2024-03-29

Abstract excerpt

Deep neural networks have been remarkably successful as models of the primate visual system. One crucial problem is that they fail to account for the strong shape-dependence of primate vision. Whereas humans base their judgements of category membership to a large extent on shape, deep networks rely much more strongly on other features such as color and texture. While this problem has been widely documented, the un...

Topics

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

Identifiers and source

Literature Corpus work: 7c7c1b39-79e3-58ed-b3cc-dfd85007f9e5
DOI: 10.1101/2024.03.25.586544

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Teaching deep networks to see shape: Lessons from a simplified visual worldDOI 10.1101/2024.03.25.586544Read

Feature blindness: a challenge for understanding and modelling visual object recognitionSemantic proximity Read

Biological convolutions improve DNN robustness to noise and generalisationSemantic proximity Read

Deep Problems with Neural Network Models of Human VisionSemantic proximity Read

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

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

A battery of image classification challenges reveals shared and distinct object categorization behavior across monkeys, humans, and deep networksSemantic proximity Read

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

Deep neural networks are not a single hypothesis but a language for expressing computational hypothesesSemantic proximity Read

Whether pattern memory can be truly realized in deep neural network?Semantic proximity Read

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

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

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