Domain generalized object detection for remote sensing images

Duraklı, Efkan and Aptoula, Erchan (2023) Domain generalized object detection for remote sensing images. In: 31st Signal Processing and Communications Applications Conference (SIU), Istanbul, Turkiye

[thumbnail of Domain_Generalized_Object_Detection_for_Remote_Sensing_Images.pdf] PDF
Restricted to Registered users only

Download (1MB) | Request a copy


Building roof type detection from remotely sensed images is a crucial task for many remote sensing applications, including urban planning and disaster management. In recent years, deep learning-based object detection approaches have demonstrated outstanding performance in this field. However, most of these approaches assume that the training and testing data are sampled from the same distribution. When there are differences between the distributions of training and test data, known as domain shift, the performance significantly degrades. In this paper, we proposed a domain generalization method to address domain shift at the instance and image level for roof type detection from remote sensing images. Furthermore, we evaluated our proposed method with IEEE Data Fusion Contest 2023 dataset. The proposed approach is the first of its kind in terms of domain generalization for remote sensing object detection.
Item Type: Papers in Conference Proceedings
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Erchan Aptoula
Date Deposited: 04 Oct 2023 15:09
Last Modified: 07 Feb 2024 14:28

Actions (login required)

View Item
View Item