ArticleiScience2022
Deep learning models fail to capture the configural nature of human shape perception.
Article in iScience, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 20 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
20 citing papers in PubMed.
- Systematic image perturbations reveal persistent gaps between human and machine vision.iScience · 2026Article
- Adaptive rightward gaze shifts support configural object recognition during perceptual challenge.iScience · 2026Article
- Behavioral differences between humans and machines arise early in visual processing.Journal of vision · 2026Article
- Visual Search Task Reveals Categorical Representation of Topological Spatial Relations Between Objects.Journal of cognition · 2026Article
- Three-dimensional shape cues affect human and artificial recognition systems differently.PloS one · 2026Article
- Potential role of developmental experience in the emergence of the parvo-magno distinction.Communications biology · 2025Article
- Human shape perception spontaneously discovers the biological origin of novel, but natural, stimuli.Journal of the Royal Society, Interface · 2025Article
- Configural processing as an optimized strategy for robust object recognition in neural networks.Communications biology · 2025Article
- A computational deep learning investigation of animacy perception in the human brain.Communications biology · 2024Article
- Deep convolutional neural networks are sensitive to face configuration.Journal of vision · 2024Article
- Meaningful Communication but not Superficial Anthropomorphism Facilitates Human-Automation Trust Calibration: The Human-Automation Trust Expectation Model (HATEM).Human factors · 2024Article
- Teaching deep networks to see shape: Lessons from a simplified visual world.PLoS computational biology · 2024Article
- Population encoding of stimulus features along the visual hierarchy.Proceedings of the National Academy of Sciences of the United States of America · 2024Article
- A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations.Neural networks : the official journal of the International Neural Network Society · 2023Article
- Drawing as a versatile cognitive tool.Nature reviews psychology · 2023Article
- Population encoding of stimulus features along the visual hierarchy.bioRxiv : the preprint server for biology · 2023Article
- Classifying Malignancy in Prostate Glandular Structures from Biopsy Scans with Deep Learning.Cancers · 2023Article
- Does training with blurred images bring convolutional neural networks closer to humans with respect to robust object recognition and internal representations?Frontiers in psychology · 2023Article
- Does the brain's ventral visual pathway compute object shape?Trends in cognitive sciences · 2022Review
- Configural relations in humans and deep convolutional neural networks.Frontiers in artificial intelligence · 2022Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
A hallmark of human object perception is sensitivity to the holistic configuration of the local shape features of an object. Deep convolutional neural networks (DCNNs) are currently the dominant models for object recognition processing in the visual cortex, but do they capture this configural sensitivity? To answer this question, we employed a dataset of animal silhouettes and created a variant of this dataset that disrupts the configuration of each object while preserving local features. While human performance was impacted by this manipulation, DCNN performance was not, indicating insensitivity to object configuration. Modifications to training and architecture to make networks more brain-like did not lead to configural processing, and none of the networks were able to accurately predict trial-by-trial human object judgements. We speculate that to match human configural sensitivity, networks must be trained to solve a broader range of object tasks beyond category recognition.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.