The University of Southampton
University of Southampton Institutional Repository

Inference and discovery in remote sensing data with features extracted using deep networks

Inference and discovery in remote sensing data with features extracted using deep networks
Inference and discovery in remote sensing data with features extracted using deep networks
We aim to develop a process by which we can extract generic features from aerial image data that can both be used to infer the presence of objects and characteristics and to discover new ways of representing the landscape. We investigate the fine-tuning of a 50-layer ResNet deep convolutional neural network that was pre-trained with ImageNet data and extracted features at several layers throughout these pre-trained and the fine-tuned networks. These features were applied to several supervised classification problems, obtaining a significant correlation between the classification accuracy and layer number. Visualising the activation of the networks’ nodes found that fine-tuning had not achieved coherent representations at later layers. We conclude that we need to train with considerably more varied data but that, even without fine tuning, features derived from a deep network can produce better classification results than with image data alone.
0302-9743
131-136
Springer
Sargent, Isabel
c0ae2d59-039b-45f2-a906-069fe46c6633
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Young, David
05bfdb8c-9675-470a-9dcb-5af247e1b4ca
Wilson, Olivia
3d8a94ec-af0f-494d-8532-12fe8d3f2859
Doidge, Charis
a1b51f53-5203-4f74-b692-75a3bfda8df7
Holland, David
7637474a-9425-4269-bff3-e072136a35f2
Atkinson, Peter M.
985bc8d3-e826-4e02-8060-8388183eb697
Bramer, Max
Petridis, Miltos
Sargent, Isabel
c0ae2d59-039b-45f2-a906-069fe46c6633
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Young, David
05bfdb8c-9675-470a-9dcb-5af247e1b4ca
Wilson, Olivia
3d8a94ec-af0f-494d-8532-12fe8d3f2859
Doidge, Charis
a1b51f53-5203-4f74-b692-75a3bfda8df7
Holland, David
7637474a-9425-4269-bff3-e072136a35f2
Atkinson, Peter M.
985bc8d3-e826-4e02-8060-8388183eb697
Bramer, Max
Petridis, Miltos

Sargent, Isabel, Hare, Jonathon, Young, David, Wilson, Olivia, Doidge, Charis, Holland, David and Atkinson, Peter M. (2017) Inference and discovery in remote sensing data with features extracted using deep networks. Bramer, Max and Petridis, Miltos (eds.) In Artificial Intelligence XXXIV: SGAI 2017. vol. 10630, Springer. pp. 131-136 . (doi:10.1007/978-3-319-71078-5_10).

Record type: Conference or Workshop Item (Paper)

Abstract

We aim to develop a process by which we can extract generic features from aerial image data that can both be used to infer the presence of objects and characteristics and to discover new ways of representing the landscape. We investigate the fine-tuning of a 50-layer ResNet deep convolutional neural network that was pre-trained with ImageNet data and extracted features at several layers throughout these pre-trained and the fine-tuned networks. These features were applied to several supervised classification problems, obtaining a significant correlation between the classification accuracy and layer number. Visualising the activation of the networks’ nodes found that fine-tuning had not achieved coherent representations at later layers. We conclude that we need to train with considerably more varied data but that, even without fine tuning, features derived from a deep network can produce better classification results than with image data alone.

Text
ImageLearn_BCSAI2017 - Accepted Manuscript
Download (206kB)
Text
ImageLearn_BCSAI2017 - Accepted Manuscript
Download (206kB)

More information

Accepted/In Press date: 5 September 2017
e-pub ahead of print date: 21 November 2017
Venue - Dates: AI-2017 Thirty-seventh SGAI International Conference on Artificial Intelligence., Peterhouse Collage, United Kingdom, 2017-12-12 - 2017-12-14

Identifiers

Local EPrints ID: 414240
URI: http://eprints.soton.ac.uk/id/eprint/414240
ISSN: 0302-9743
PURE UUID: 658d1d10-684f-49e5-8566-11537616015d
ORCID for Jonathon Hare: ORCID iD orcid.org/0000-0003-2921-4283

Catalogue record

Date deposited: 20 Sep 2017 16:31
Last modified: 07 Oct 2020 05:26

Export record

Altmetrics

Contributors

Author: Isabel Sargent
Author: Jonathon Hare ORCID iD
Author: David Young
Author: Olivia Wilson
Author: Charis Doidge
Author: David Holland
Author: Peter M. Atkinson
Editor: Max Bramer
Editor: Miltos Petridis

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×