Self-Supervised Learning of Color Constancy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909167327903744 |
|---|---|
| author | Ernst, Markus R. López, Francisco M. Aubret, Arthur Fleming, Roland W. Triesch, Jochen |
| author_facet | Ernst, Markus R. López, Francisco M. Aubret, Arthur Fleming, Roland W. Triesch, Jochen |
| contents | Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully characterized in humans, it is still unclear how the visual system acquires this ability during development. Here, we present a first study showing that CC develops in a neural network trained in a self-supervised manner through an invariance learning objective. During learning, objects are presented under changing illuminations, while the network aims to map subsequent views of the same object onto close-by latent representations. This gives rise to representations that are largely invariant to the illumination conditions, offering a plausible example of how CC could emerge during human cognitive development via a form of self-supervised learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08127 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Learning of Color Constancy Ernst, Markus R. López, Francisco M. Aubret, Arthur Fleming, Roland W. Triesch, Jochen Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully characterized in humans, it is still unclear how the visual system acquires this ability during development. Here, we present a first study showing that CC develops in a neural network trained in a self-supervised manner through an invariance learning objective. During learning, objects are presented under changing illuminations, while the network aims to map subsequent views of the same object onto close-by latent representations. This gives rise to representations that are largely invariant to the illumination conditions, offering a plausible example of how CC could emerge during human cognitive development via a form of self-supervised learning. |
| title | Self-Supervised Learning of Color Constancy |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.08127 |