Article

Human shape representations are not an emergent property of learning to classify objects

2021-12-15

Abstract excerpt

Humans are particularly sensitive to changes in the relationships between parts of objects. It remains unclear why this is. One hypothesis is that relational features are highly diagnostic of object categories and emerge as a result of learning to classify objects. We tested this by analysing the internal representations of supervised convolutional neural networks (CNNs) trained to classify large sets of objects....

Topics

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

Identifiers and source

Literature Corpus work: 8baaa543-33e7-533e-9274-5be748f87b2a
DOI: 10.1101/2021.12.14.472546

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Human shape representations are not an emergent property of learning to classify objectsDOI 10.1101/2021.12.14.472546Read

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

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

Abstract representations emerge naturally in neural networks trained to perform multiple tasksSemantic proximity Read

Objects, Faces, and Spaces: Organizational Principles of Visual Object Perception as Evidenced by Individual Differences in BehaviorSemantic proximity Read

How we draw and recognize things that don’t existSemantic proximity Read

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

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

Behavioral signatures of face perception emerge in deep neural networks optimized for face recognitionSemantic proximity Read

Using Compositionality to Learn Many Categories from Few ExamplesSemantic proximity Read

Understanding transformation tolerant visual object representations in the human brain and convolutional neural networksSemantic proximity Read

One shot generalization in humans revealed through a drawing taskSemantic proximity Read

An image-computable model of human visual shape similaritySemantic proximity Read