Article

Behavioral signatures of face perception emerge in deep neural networks optimized for face recognition

2022-11-24

Abstract excerpt

Human face recognition is highly accurate, and exhibits a number of distinctive and well documented behavioral “signatures” such as the use of a characteristic representational space, the disproportionate performance cost when stimuli are presented upside down, and the drop in accuracy for faces from races the participant is less familiar with. These and other phenomena have long been taken as evidence that face r...

Topics

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

Uncategorized literature

Identifiers and source

Literature Corpus work: e137f996-2a9e-568c-81db-0cd08c11a666
DOI: 10.1101/2022.11.23.517478

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Behavioral signatures of face perception emerge in deep neural networks optimized for face recognitionDOI 10.1101/2022.11.23.517478Read

Face recognition depends on specialized mechanisms tuned to view-invariant facial features: Insights from deep neural networks optimized for face or object recognitionSemantic proximity Read

Mooney Face Image Processing in Deep Convolutional Neural Networks Compared to HumansSemantic proximity Read

Brain-like functional specialization emerges spontaneously in deep neural networksSemantic proximity Read

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

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

Trade-off between performance and human-like perception in face recognition modelsSemantic proximity Read

Deep learning algorithms reveal a new visual-semantic representation of familiar faces in human perception and memorySemantic proximity Read

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

Face identity selectivity in the deep neural network and human brainSemantic proximity Read

Diverse Visual Experience Promotes Integrated and Human-Aligned Face Representations in Deep Neural NetworksSemantic proximity Read

Computational insights into human perceptual expertise for familiar and unfamiliar face recognitionSemantic proximity Read