Article

Trade-off between performance and human-like perception in face recognition models

2026-08-10

Abstract excerpt

<p>Deep learning models for face recognition are widely adopted in cognitive neuroscience, yet it is not well understood whether their excellent performance means they “see” faces like humans. Here, we collected a substantial dataset of human face-similarity judgments to assess how well prominent face recognition models align with human perception. We found that models with high—but not the highest—recognition per...

Topics

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

dental development and anomalies

Identifiers and source

Literature Corpus work: ab13a1ef-e98f-5185-8404-8e58a8bc9f87
DOI: 10.31234/osf.io/bz3f9_v4

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Trade-off between performance and human-like perception in face recognition modelsDOI 10.31234/osf.io/bz3f9_v4Read

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

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

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

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

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

Predicting visual working memory errors with a priori measures of representational geometry from human and artificial systemsSemantic 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

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

Unraveling other-race face perception with GAN-based image reconstructionSemantic proximity Read

Capturing and modifying the perceived traits of all possible facesSemantic proximity Read

Face dissimilarity judgements are predicted by representational distance in morphable and image-computable modelsSemantic proximity Read

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