Unsupervised learning predicts human perception and misperception of gloss
Bibliographic Data
| ID | 4720006 |
|---|---|
| Authors | Katherine R Storrs (0000-0001-9573-8654, Justus-Liebig-Universität Gießen, corresponding author), Barton L Anderson (0000-0003-0313-4285, The University of Sydney), R W Fleming (0000-0001-5033-5069, Justus-Liebig-Universität Gießen) |
| Year | 2021 |
| Volume | 5 |
| Issue | 10 |
| Pages | 1402-1417 |
| Publication date | 2021-05-06 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Nature Human Behaviour (JOURNAL) |
| Journal identifiers | ISSN: 2397-3374 • E-ISSN: 2397-3374 |
| Publisher | Springer Science and Business Media LLC (PUBLISHER) |
| DOI | 10.1038/s41562-021-01097-6 |
| PMID | 33958744 |
| OpenAlex | W3157521173 |
| Language | EN |
| Citations received | 3 |
| References cited | 98 |
Reflectance, lighting and geometry combine in complex ways to create images. How do we disentangle these to perceive individual properties, such as surface glossiness? We suggest that brains disentangle properties by learning to model statistical structure in proximal images. To test this hypothesis, we trained unsupervised generative neural networks on renderings of glossy surfaces and compared their representations with human gloss judgements. The networks spontaneously cluster images according to distal properties such as reflectance and illumination, despite receiving no explicit information about these properties. Intriguingly, the resulting representations also predict the specific patterns of 'successes' and 'errors' in human perception. Linearly decoding specular reflectance from the model's internal code predicts human gloss perception better than ground truth, supervised networks or control models, and it predicts, on an image-by-image basis, illusions of gloss perception caused by interactions between material, shape and lighting. Unsupervised learning may underlie many perceptual dimensions in vision and beyond
Artificial neural network · Cognitive psychology · Computer vision · Generative grammar · Generative model · Illusion · Optics · Perception · Physics · Specular reflection · Aesthetic Perception and Analysis · Color Science and Applications · Computer Science · Neuroscience · Psychology · Visual perception and processing mechanisms · Artificial Intelligence
The free-energy principle
Representation Learning
Pingouin
Reducing the Dimensionality of Data with Neural Networks
ImageNet Large Scale Visual Recognition Challenge
Some informational aspects of visual perception.
Deep learning
Letter perception emerges from unsupervised deep learning and recycling of natural image features
Material category of visual objects computed from specular image structure
| Unique citing works | 3 |
|---|---|
| Citations per year | 0,6 |
| Citation span | 2021 - 2023 (3) |
| Citation velocity | historical |
| Highly cited | No |
| Citation types | Neutral: 2 |