Javed, M. and Mihaylova, L. orcid.org/0000-0001-5856-2223 (2019) Leveraging uncertainty in adversarial learning to improve deep learning based segmentation. In: Proceedings of IEEE 13th Symposium Sensor Data Fusion. 13th Symposium Sensor Data Fusion, 15-17 Oct 2019, Bonn, Germany. Institute of Electrical and Electronics Engineers (IEEE) ISBN 9781728150864
Abstract
This paper proposes a new framework that combines Bayesian SegNet with adversarial learning to obtain high quality segmented objects of interest. The proposed architecture takes in the form of two discriminator networks that are trained separately. The first network discriminates between segmentation maps coming either from the SegNet or the ground truth. The second network discriminates between the model uncertainty obtained from SegNet and an ideal solution that does not include uncertainty. The process is very similar to the fusion of sensor information for better decision making. Uncertainty is considered as a measure of mistakes. Hence, learning from it will help improve the performance of neural networks. Our results show that we obtain higher accuracies compared to Bayesian SegNet. Training is performed on a small-sized dataset called CamVid and a large-sized dataset Sun RGB-D. The paper shows that dealing with uncertainties is beneficial for decision making in neural networks, especially in applications with highly uncertain environments. Examples include self-driving cars and medical imaging in cancer treatment.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Reproduced in accordance with the publisher's self-archiving policy. |
Keywords: | segmentation; adversarial learning; deep neural networks; Bayesian SegNet; epistemic uncertainty |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Oct 2019 07:59 |
Last Modified: | 28 Nov 2020 01:51 |
Status: | Published online |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Refereed: | Yes |
Identification Number: | 10.1109/SDF.2019.8916632 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:152068 |