Shop : Details
Shop
Details
February 2025
eBook (PDF)
Nikhil Kapoor
Improving Robustness of Perception DNNs in Various Domains
In recent years, deep learning has gained tremendous popularity for solving various challenges in highly automated driving, such as environment perception, sensor fusion, motion planning, etc. In this context, semantic segmentation appears to be a vital task that helps identify objects in a scene around the car. However, deep learning models frequently struggle with robustness concerning diverse input distribution shifts, including sensor noise, photometric changes, motion blur, and adversarial attacks. This lack of robustness poses a substantial safety challenge that must be addressed to ensure the reliability and safety of highly automated driving systems.
This thesis focuses on the lack of robustness issue in camera-based semantic segmentation tasks. We begin by benchmarking two state-of-the-art semantic segmentation models for their resilience to input corruptions and adversarial attacks. The benchmarking uncovers robustness issues in both models, with adversarial attacks inflicting more damage than corruptions. We then propose three novel methods to enhance these models’ robustness across a variety of attacks and corruptions simultaneously. Detailed evaluations and research directions are presented for each method and open the door to improved safety and reliability of autonomous systems in complex environments.
This thesis focuses on the lack of robustness issue in camera-based semantic segmentation tasks. We begin by benchmarking two state-of-the-art semantic segmentation models for their resilience to input corruptions and adversarial attacks. The benchmarking uncovers robustness issues in both models, with adversarial attacks inflicting more damage than corruptions. We then propose three novel methods to enhance these models’ robustness across a variety of attacks and corruptions simultaneously. Detailed evaluations and research directions are presented for each method and open the door to improved safety and reliability of autonomous systems in complex environments.
Keywords: robustness; adversarial defense; computer vision; corruption robustness; convolutional neural networks
Mitteilungen aus dem Institut für Nachrichtentechnik der Technischen Universität Braunschweig
Edited by Prof. Dr.-Ing. U. Reimers, Prof. Dr.-Ing. T. Kürner and Prof. Dr.-Ing. T. Fingscheidt, Braunschweig
Volume 84
Other formats
Print version: 978-3-8440-9906-5
DOI 10.2370/9783844098976
You need Adobe Reader, to view these files. Here you will find a little help and information for downloading the PDF files.
Please note that the online documents cannot be printed or edited.
Please also see further information at: Help and Information.
Please also see further information at: Help and Information.
| Document |  | Document | ||
| Type |  | |||
| Costs |  | 44,10 € | ||
| Action |  | Purchase in obligation and download the file | ||
| Document |  | Table of contents | ||
| Type | | |||
| Costs |  | free | ||
| Action |  | Download the file | ||
User settings for registered online customers (online documents)
You can change your address details here and access documents you have already ordered.
User
Not logged in
Shaker Verlag GmbH
Am Langen Graben 15a
52353 Düren
Germany
Am Langen Graben 15a
52353 Düren
Germany
Mon. - Thurs. 8:00 a.m. to 4:00 p.m.
Fri. 8:00 a.m. to 3:00 p.m.
Fri. 8:00 a.m. to 3:00 p.m.
Contact us. We will be happy to help you.
