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...

Celý popis

Uloženo v:
Podrobná bibliografie
Hlavní autor: Guirguis, Karim
Médium: E-kniha
Jazyk:angličtina
Vydáno: KIT Scientific Publishing 2025
Edice:Schriftenreihe Automatische Sichtprüfung und Bildverarbeitung
Témata:
Computer science
Computer Vision
Computing and Information Technology
Deep Learning
Few Shot Learning
Mathematical theory of computation
Maths for computer scientists
Object Detection
Objekt-Erkennung
Optical Inspection
Optische Inspektion
Tiefes Lernen
ISBN:9783731513896, 3731513897
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISBN:9783731513896
3731513897
DOI:10.5445/KSP/1000174849