Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving

Beschreibung

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.

Autor*in

Tobias Michael Kalb

Themen in »Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving«

Kontinuierliches Lernen Katastrophales Vergessen Semantische Segmentierung Automatisiertes Fahren Deep Learning Continual Learning Deep Learning Catastrophic Forgetting Semantic Segmentation Automated Driving

Stimmen zu »Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving«

Details

Link teilen