Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving

Deep learning excels at extracting complex patterns but faces catastrophic forgetting when fine-tuned on new data. This book investigates how class- and domain-incremental learning affect neural networks for automated driving, identifying semantic shifts and feature changes as key factors. Tools for quantitatively measuring forgetting are selected and used to show how strategies like image augmentation, pretraining, and architectural adaptations mitigate catastrophic forgetting.

Product details

• Authors: Tobias Michael Kalb
• Publisher: KIT Scientific Publishing
• Languages: English
• Product format: Paperback / Softback
• Released: 21.10.2024
• EAN: 9783731513735
• ISBN: 978-3-7315-1373-5
• No. of pages: 236
• Dimensions: 148 mm x 14 mm x 210 mm
• Weight: 450 g
• Illustrations: graph. Darst.
• Series: Karlsruher Schriften zur Anthropomatik / Lehrstuhl für Interaktive Echtzeitsysteme, Karlsruher Institut für Technologie ; Fraunhofer-Inst. für Optronik, Systemtechnik und Bildauswertung IOSB Karlsruhe
• Subjects: Guides; Natural sciences, medicine, IT, technology > IT, data processing