Killick, G., Henderson, P. , Siebert, P. and Aragon Camarasa, G. (2023) Foveation in the Era of Deep Learning. In: 34th British Machine Vision Conference (BMVC 2023), Aberdeen, UK, 20-24 Nov 2023,
Text
307005.pdf - Published Version 511kB | |
Text
307005Suppl.pdf - Supplemental Material 190kB |
Publisher's URL: https://proceedings.bmvc2023.org/703/
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.
Item Type: | Conference Proceedings |
---|---|
Status: | Published |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Siebert, Dr Paul and Aragon Camarasa, Dr Gerardo and Henderson, Dr Paul and Killick, George |
Authors: | Killick, G., Henderson, P., Siebert, P., and Aragon Camarasa, G. |
College/School: | College of Science and Engineering > School of Computing Science |
Copyright Holders: | Copyright © 2023 the authors |
First Published: | First published in The 34th British Machine Vision Conference Proceedings |
Publisher Policy: | Reproduced in accordance with the publisher copyright policy |
University Staff: Request a correction | Enlighten Editors: Update this record