Human face perception reflects inverse-generative and naturalistic discriminative objectives

• URL: http://arxiv.org/abs/2605.12619v1
• Date: Tue, 12 May 2026 18:06:57 GMT
• Title: Human face perception reflects inverse-generative and naturalistic discriminative objectives
• Abstract summary: Deep neural networks offer mechanistic hypotheses for human face perception.<n>We compared six neural network models sharing an architecture but trained on distinct tasks.<n>We tested model predictions against face-dissimilarity judgments from 864 human participants.
• Score: 2.4126189670630733
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The perceptual representations supporting our ability to recognize faces remain a computational mystery. Deep neural networks offer mechanistic hypotheses for human face perception, but theoretically distinct models often make indistinguishable representational predictions for randomly sampled faces. To expose diagnostic differences among these hypotheses, we compared six neural network models sharing an architecture but trained on distinct tasks, using face pairs optimized to elicit contrasting model predictions ("controversial" pairs) alongside randomly sampled pairs. We tested model predictions against face-dissimilarity judgments from 864 human participants across stimulus sets differing in realism and pose variation. Models prioritizing high-level, invariant structures (trained via inverse rendering, face identification, or object classification) most robustly matched human judgments. Furthermore, models trained on natural images typically outperformed synthetic-trained counterparts. Together, these findings suggest that human face perception is shaped by mechanisms that infer latent causes of facial appearance, discount nuisance variation, and are tuned by natural image statistics.

Related papers

• AlignFace: Human-Aligned Face Similarity Metric with Interpretable Concept Relations [13.228617286387887]
  We introduce the FACETS dataset and propose AlignFace, an interpretable, human-aligned, face similarity metric.<n>Experiments found AlignFace significantly improves alignment with human subpopulation perceptions compared to baseline metrics.
  arXiv  Detail & Related papers  (2026-08-14T09:36:28Z)
• AI-guided stimuli discovery and generation to optimize facial emotion perception studies in autism [3.933503880903322]
  We show that autistic-neurotypical differences in emotion judgments were concentrated in a small subset of diagnostic facial expressions.<n>We trained population-specific artificial neural network models to predict image-level judgments for autistic and neurotypical participants.<n>We then used the same models with a generative adversarial network to transform diagnostic images toward greater predicted group agreement.
  arXiv  Detail & Related papers  (2026-07-09T14:29:31Z)
• Human-level 3D shape perception emerges from multi-view learning [63.048728487674815]
  We develop a modeling framework that predicts human 3D shape inferences for arbitrary objects.<n>We achieve this with a novel class of neural networks trained using a visual-spatial objective over naturalistic sensory data.<n>We find that human-level 3D perception can emerge from a simple, scalable learning objective over naturalistic visual-spatial data.
  arXiv  Detail & Related papers  (2026-02-19T18:56:05Z)
• Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering Human Perceptual Variability on Facial Expressions [9.172281969351795]
  This study investigates the phenomenon of high perceptual variability-where individuals exhibit significant differences in emotion categorization even when viewing the same stimulus.<n>Inspired by the similarity between ANNs and human perception, we hypothesize that facial expression samples that are ambiguous for ANN classifiers also elicit divergent perceptual judgments among human observers.<n>Our findings establish a systematic link between ANN decision boundaries and human perceptual variability, offering new insights into personalized modeling of emotional interpretation.
  arXiv  Detail & Related papers  (2025-07-19T09:12:13Z)
• Epistemic Uncertainty for Generated Image Detection [107.62647907393377]
  We introduce a novel framework for AI-generated image detection through epistemic uncertainty, aiming to address critical security concerns in the era of generative models.<n>Our key insight stems from the observation that distributional discrepancies between training and testing data manifest distinctively in the epistemic uncertainty space of machine learning models.
  arXiv  Detail & Related papers  (2024-12-08T11:32:25Z)
• Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments [0.5735035463793008]
  We show that a neural network trained to invert a 3D-face-model graphics is more human-aligned than the same architecture trained on identification, classification, or autoencoding. Our results indicate that a neural network trained to invert a 3D-face-model graphics is more human-aligned than the same architecture trained on identification, classification, or autoencoding.
  arXiv  Detail & Related papers  (2022-11-28T04:17:35Z)
• CIAO! A Contrastive Adaptation Mechanism for Non-Universal Facial Expression Recognition [80.07590100872548]
  We propose Contrastive Inhibitory Adaptati On (CIAO), a mechanism that adapts the last layer of facial encoders to depict specific affective characteristics on different datasets. CIAO presents an improvement in facial expression recognition performance over six different datasets with very unique affective representations.
  arXiv  Detail & Related papers  (2022-08-10T15:46:05Z)
• Evaluation of Human and Machine Face Detection using a Novel Distinctive Human Appearance Dataset [0.76146285961466]
  We evaluate current state-of-the-art face-detection models in their ability to detect faces in images. The evaluation results show that face-detection algorithms do not generalize well to diverse appearances.
  arXiv  Detail & Related papers  (2021-11-01T02:20:40Z)
• SynFace: Face Recognition with Synthetic Data [83.15838126703719]
  We devise the SynFace with identity mixup (IM) and domain mixup (DM) to mitigate the performance gap. We also perform a systematically empirical analysis on synthetic face images to provide some insights on how to effectively utilize synthetic data for face recognition.
  arXiv  Detail & Related papers  (2021-08-18T03:41:54Z)
• Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models [86.79402670904338]
  We evaluate the performance of four state-of-the-art deep face recognition models in the presence of image distortions. We have observed that image distortions have a relationship with the performance gap of the model across different subgroups.
  arXiv  Detail & Related papers  (2021-08-14T16:49:05Z)
• A Linked Aggregate Code for Processing Faces (Revised Version) [0.0]
  A model of face representation is compared to experimental data on the perception of facial similarity. The results suggest that the LAC based similarity measure may offer a fertile starting point for further modelling studies of face representation in higher visual areas.
  arXiv  Detail & Related papers  (2020-09-17T13:29:25Z)
• Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction [49.254162397086006]
  We study explanations based on visual saliency in an image-based age prediction task. We find that presenting model predictions improves human accuracy. However, explanations of various kinds fail to significantly alter human accuracy or trust in the model.
  arXiv  Detail & Related papers  (2020-07-23T20:39:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.