Foveation in the Era of Deep Learning
George W Killick (University of Glasgow),* Paul Henderson (University of Glasgow), Jan Paul Siebert (University of Glasgow), Gerardo Aragon-Camarasa (University of Glasgow)
The 34th British Machine Vision Conference
Abstract
In this paper, we tackle the challenge of actively attending to visual scenes using a foveated sensor. We introduce an end-to-end differentiable foveated active vision architecture that leverages a graph convolutional network to process foveated images, and a simple yet effective formulation for foveated image sampling. Our model learns to iteratively attend to regions of the image relevant for classification. We conduct detailed experiments on a variety of image datasets, comparing the performance of our method with previous approaches to foveated vision while measuring how the impact of different choices, such as the degree of foveation, and the number of fixations the network performs, affect object recognition performance. We find that our model outperforms a state-of-the-art CNN and foveated vision architectures of comparable parameters and a given pixel or computation budget.Video
Citation
@inproceedings{Killick_2023_BMVC,
author = {George W Killick and Paul Henderson and Jan Paul Siebert and Gerardo Aragon-Camarasa},
title = {Foveation in the Era of Deep Learning},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0703.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by