Copertina

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...

Descrizione completa

Salvato in:
Autore principale: Kalb, Tobias Michael
Natura: Online
Lingua:inglese
Pubblicazione: KIT Scientific Publishing 2024
Soggetti:
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
Accesso online:https://library.oapen.org/handle/20.500.12657/94140
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
Riassunto: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.

Documenti analoghi