Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving

Download or read book Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving written by Kalb, Tobias Michael and published by KIT Scientific Publishing. This book was released on 2024-10-21 with total page 236 pages. Available in PDF, EPUB and Kindle. Book excerpt: 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.