ArticleNature communications2024
Improved modeling of human vision by incorporating robustness to blur in convolutional neural networks.
Article in Nature communications, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 23 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
23 citing papers in PubMed, 32 citations in OpenAlex.
- Systematic image perturbations reveal persistent gaps between human and machine vision.iScience · 2026Article
- Eccentricity-Constrained CNN Training Reveals Adaptive Information Coding Around the Visual Field.ArXiv · 2026Article
- Nondestructive Detection of Foreign Matter in Pu-erh Ripe Tea Based on Deep Learning.Foods (Basel, Switzerland) · 2026Article
- Category selectivity observed in the human brain is distinct from category selectivity observed in artificial neural networks.bioRxiv : the preprint server for biology · 2026Article
- Linking retinal sampling in neural encoding models to temporal profiles of visual processing in humans.PLoS computational biology · 2026Article
- Article
- Impact of Simulated Artifacts on the Classification Performance of Apical Views in Transthoracic Echocardiography Using Convolutional Neural Networks.Bioengineering (Basel, Switzerland) · 2026Article
- Exposure to naturalistic occlusion promotes generalized, human-like robustness in deep neural networks.bioRxiv : the preprint server for biology · 2026Article
- Individual differences in artificial neural networks capture individual differences in human behavior.bioRxiv : the preprint server for biology · 2026Article
- Behavioral differences between humans and machines arise early in visual processing.Journal of vision · 2026Article
- Three-dimensional shape cues affect human and artificial recognition systems differently.PloS one · 2026Article
- Generating metamers of human scene understanding.... International Conference on Learning Representations · 2026Article
- Computationally Probing the Role of Time-Limited Neuronal Plasticity in Early Visual Development.Developmental science · 2026Article
- Computational origins of shape perception.PLoS computational biology · 2025Article
- Human-like individual differences emerge from random weight initializations in neural networks.bioRxiv : the preprint server for biology · 2025Article
- A compressed code for memory discrimination.bioRxiv : the preprint server for biology · 2025Article
- Category-specific perceptual learning of robust object recognition modelled using deep neural networks.PLoS computational biology · 2025Article
- Fast and robust visual object recognition in young children.Science advances · 2025Article
- Potential role of developmental experience in the emergence of the parvo-magno distinction.Communications biology · 2025Article
- Transferable polychromatic optical encoder for neural networks.Nature communications · 2025Article
Corrections and comments
- Update of
Authors and funding
2 authors at 2 institutions in 2 countries.
Funding
Abstract
Whenever a visual scene is cast onto the retina, much of it will appear degraded due to poor resolution in the periphery; moreover, optical defocus can cause blur in central vision. However, the pervasiveness of blurry or degraded input is typically overlooked in the training of convolutional neural networks (CNNs). We hypothesized that the absence of blurry training inputs may cause CNNs to rely excessively on high spatial frequency information for object recognition, thereby causing systematic deviations from biological vision. We evaluated this hypothesis by comparing standard CNNs with CNNs trained on a combination of clear and blurry images. We show that blur-trained CNNs outperform standard CNNs at predicting neural responses to objects across a variety of viewing conditions. Moreover, blur-trained CNNs acquire increased sensitivity to shape information and greater robustness to multiple forms of visual noise, leading to improved correspondence with human perception. Our results provide multi-faceted neurocomputational evidence that blurry visual experiences may be critical for conferring robustness to biological visual systems.
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.