Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
KIT Scientific Publishing
Abstract
Description
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.
Keywords
Automated Driving; Semantic Segmentation; Catastrophic Forgetting; Continual Learning; Deep Learning; Automatisiertes Fahren; Semantische Segmentierung; Katastrophales Vergessen; Kontinuierliches Lernen, thema EDItEUR::U Computing and Information Technology::UY Computer science::UYA Mathematical theory of computation::UYAM Maths for computer scientists