Artículos relacionados a Principles of Catastrophic Forgetting for Continual...

Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving (Karlsruher Schriften zur Anthropomatik) - Tapa blanda

Kalb, Tobias Michael

 
9783731513735: Principles of Catastrophic Forgetting for Continual Semantic Segmentation in Automated Driving (Karlsruher Schriften zur Anthropomatik)

Sinopsis

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.

"Sinopsis" puede pertenecer a otra edición de este libro.