loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Daniel Wiens 1 ; 2 and Barbara Hammer 1

Affiliations: 1 Bielefeld University, Bielefeld, Germany ; 2 Mercedes-Benz AG, Stuttgart, Germany

Keyword(s): Adversarial Training, Adversarial Attack, Step Size Control, Semantic Segmentation, Deep Neural Network.

Abstract: Even though deep neural networks succeed on many different tasks including semantic segmentation, they lack on robustness against adversarial examples. To counteract this exploit, often adversarial training is used. However, it is known that adversarial training with weak adversarial attacks (e.g. using the Fast Gradient Sign Method) does not improve the robustness against stronger attacks. Recent research shows that it is possible to increase the robustness of such single-step methods by choosing an appropriate step size during the training. Finding such a step size, without increasing the computational effort of single-step adversarial training, is still an open challenge. In this work we address the computationally particularly demanding task of semantic segmentation and propose a new step size control algorithm that increases the robustness of single-step adversarial training. The proposed algorithm does not increase the computational effort of single-step adversarial training co nsiderably and also simplifies training, because it is free of meta-parameter. We show that the robustness of our approach can compete with multi-step adversarial training on two popular benchmarks for semantic segmentation. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.235.65.220

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Wiens, D. and Hammer, B. (2022). Single-step Adversarial Training for Semantic Segmentation. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - ICPRAM, ISBN 978-989-758-549-4; ISSN 2184-4313, pages 179-187. DOI: 10.5220/0010788400003122

@conference{icpram22,
author={Daniel Wiens. and Barbara Hammer.},
title={Single-step Adversarial Training for Semantic Segmentation},
booktitle={Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - ICPRAM,},
year={2022},
pages={179-187},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010788400003122},
isbn={978-989-758-549-4},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - ICPRAM,
TI - Single-step Adversarial Training for Semantic Segmentation
SN - 978-989-758-549-4
IS - 2184-4313
AU - Wiens, D.
AU - Hammer, B.
PY - 2022
SP - 179
EP - 187
DO - 10.5220/0010788400003122