Copertina

Towards Learning Object Detectors with Limited Data for Industrial Applications

In this dissertation, three novel Generalized Few-Shot Object Detection (G-FSOD) approaches are presented to minimize the forgetting of previously learned classes while learning new classes with limited data. The first two approaches reduce the forgetting of base classes if they are still available...

Descrizione completa

Salvato in:
Autore principale: Guirguis, Karim
Natura: Online
Lingua:inglese
Pubblicazione: KIT Scientific Publishing 2025
Soggetti:
Optical Inspection; Object Detection; Deep Learning; Few Shot Learning; Optische Inspektion; Objekt-Erkennung; Computer Vision; Tiefes 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/20.500.12657/100728
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
Riassunto:In this dissertation, three novel Generalized Few-Shot Object Detection (G-FSOD) approaches are presented to minimize the forgetting of previously learned classes while learning new classes with limited data. The first two approaches reduce the forgetting of base classes if they are still available during training. The third approach, for scenarios without base data, uses knowledge distillation to improve the knowledge transfer.

Documenti analoghi