Article

Learning to See Like a Child: Why Viewpoint Diversity is Fundamental for Human-Aligned Object Recognition

2026-05-27

Abstract excerpt

Deep convolutional neural networks match human accuracy on standard object recognition tasks but fail to recognize familiar objects from novel view-points. Humans, however, develop viewpoint-invariant recognition at an early age through diverse visual experience. This gap in visual experience may explain why models diverge from humans in object recognition. Holding dataset size constant, we show that greater viewp...

Topics

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

Identifiers and source

Literature Corpus work: db620c5b-5e5c-5ed6-ae81-e2b0c9547930
DOI: 10.64898/2026.05.27.727784

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Learning to See Like a Child: Why Viewpoint Diversity is Fundamental for Human-Aligned Object RecognitionDOI 10.64898/2026.05.27.727784Read

Cross-cue reconstruction of perceived 3D object structure from human visual cortexSemantic proximity Read

The representational geometry of out‐of‐distribution generalization in primary visual cortex and artificial neural networksSemantic proximity Read

Efficient task generalization and humanlike face perception in models that learn to discriminate face geometrySemantic proximity Read

How Visual Experience Shapes Face Processing: Divergent Representational Strategies Emerge from Specialized and Diverse Visual Diets in Artificial Neural NetworksSemantic proximity Read

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

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

Exposure to naturalistic occlusion promotes generalized, human-like robustness in deep neural networksSemantic proximity Read

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

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

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

Concurrent emergence of view invariance, sensitivity to critical features, and identity face classification through visual experience: Insights from deep learning algorithmsSemantic proximity Read

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