Volltext-Downloads (blau) und Frontdoor-Views (grau)

Continual Learning in Object Detection

  • Object detection concerns the classification and localization of objects in an image. To cope with changes in the environment, such as when new classes are added or a new domain is encountered, the detector needs to update itself with the new information while retaining knowledge learned in the past. Previous works have shown that training the detector solely on new data would produce a severe "forgetting" effect, in which the performance on past tasks deteriorates through each new learning phase. However, in many cases, storing and accessing past data is not possible due to privacy concerns or storage constraints. This project aims to investigate promising continual learning strategies for object detection without storing and accessing past training images and labels. We show that by utilizing the pseudo-background trick to deal with missing labels, and knowledge distillation to deal with missing data, the forgetting effect can be significantly reduced in both class-incremental and domain-incremental scenarios. Furthermore, an integration of a small latent replay buffer can result in a positive backward transfer, indicating the enhancement of past knowledge when new knowledge is learned.

Export metadata

Additional Services

Search Google Scholar Check availability


Show usage statistics
Document Type:Master's Thesis
Author:Huy Tran Tien
Referee:Duc Bach Ha, Paul Plöger, Sebastian Houben
Granting Institution:Hochschule Bonn-Rhein-Sieg, Fachbereich Informatik
Date of first publication:2023/09/19
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Theses, student research papers:Hochschule Bonn-Rhein-Sieg / Fachbereich Informatik
Entry in this database:2023/09/29