Emergence of Foveal Image Sampling from Learning to Attend in Visual Scenes
Abstract
We describe a neural attention model with a learnable retinal sampling lattice. The model is trained on a visual search task requiring the classification of an object embedded in a visual scene amidst background distractors using the smallest number of fixations. We explore the tiling properties that emerge in the model's retinal sampling lattice after training. Specifically, we show that this lattice resembles the eccentricity dependent sampling lattice of the primate retina, with a high resolution region in the fovea surrounded by a low resolution periphery. Furthermore, we find conditions where these emergent properties are amplified or eliminated providing clues to their function.
Cite
Text
Cheung et al. "Emergence of Foveal Image Sampling from Learning to Attend in Visual Scenes." International Conference on Learning Representations, 2017.Markdown
[Cheung et al. "Emergence of Foveal Image Sampling from Learning to Attend in Visual Scenes." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/cheung2017iclr-emergence/)BibTeX
@inproceedings{cheung2017iclr-emergence,
title = {{Emergence of Foveal Image Sampling from Learning to Attend in Visual Scenes}},
author = {Cheung, Brian and Weiss, Eric and Olshausen, Bruno A.},
booktitle = {International Conference on Learning Representations},
year = {2017},
url = {https://mlanthology.org/iclr/2017/cheung2017iclr-emergence/}
}