Towards Learning Object Detectors with Limited Data for Industrial Applications
| dc.contributor.author | Guirguis, Karim | |
| dc.date.accessioned | 2025-04-14T12:06:32Z | |
| dc.date.available | 2025-04-14T12:06:32Z | |
| dc.date.issued | 2025 | |
| dc.identifier.uri | https://library.oapen.org/handle/20.500.12657/100728 | |
| dc.description.abstract | 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. | en_US |
| dc.language | English | en_US |
| dc.relation.ispartofseries | Schriftenreihe Automatische Sichtprüfung und Bildverarbeitung | en_US |
| dc.subject.classification | thema EDItEUR::U Computing and Information Technology::UY Computer science::UYA Mathematical theory of computation::UYAM Maths for computer scientists | en_US |
| dc.subject.other | Optical Inspection; Object Detection; Deep Learning; Few Shot Learning; Optische Inspektion; Objekt-Erkennung; Computer Vision; Tiefes Lernen | en_US |
| dc.title | Towards Learning Object Detectors with Limited Data for Industrial Applications | en_US |
| dc.type | book | |
| oapen.identifier.doi | 10.5445/KSP/1000174849 | en_US |
| oapen.relation.isPublishedBy | 44e29711-8d53-496b-85cc-3d10c9469be9 | en_US |
| oapen.series.number | 8 | en_US |
| oapen.pages | 262 | en_US |
