Human face perception aligns with neural networks trained on inverse-generative and naturalistic discriminative tasks, as these best predict human dissimilarity judgments on controversial and random face pairs.
Rajat Raina, Andrew Y
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
support 1representative citing papers
Hybrid JEMs at intermediate generative-discriminative balance maximize human alignment on perceptual similarity, gloss, uncertainty, robustness, cue conflict, and feature attribution benchmarks.
citing papers explorer
-
Human face perception reflects inverse-generative and naturalistic discriminative objectives
Human face perception aligns with neural networks trained on inverse-generative and naturalistic discriminative tasks, as these best predict human dissimilarity judgments on controversial and random face pairs.
-
Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
Hybrid JEMs at intermediate generative-discriminative balance maximize human alignment on perceptual similarity, gloss, uncertainty, robustness, cue conflict, and feature attribution benchmarks.