A distance transform based loss function for the semantic segmentation of very high resolution remote sensing images

Gül, Furkan and Aptoula, Erchan (2024) A distance transform based loss function for the semantic segmentation of very high resolution remote sensing images. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2024), Athens, Greece

Full text not available from this repository. (Request a copy)

Abstract

Accurately segmenting region boundaries in complex and high resolution remote sensing scenes, with often a large number of relatively small structures and objects remains a challenge; since conventional loss functions such as Cross-Entropy and Intersection-over-Union often neglect boundary precision and focus instead on the alignment of the entire estimated region. This paper presents a new distance transform-based loss function designed especially to focus on boundary quality enhancement. It is validated with the ISPRS very high spatial resolution Vaihingen and Potsdam remote sensing datasets using a U-Net model with a ResNet-50 encoder. Preliminary results show that the proposed loss function outperforms widely used loss functions across multiple evaluation metrics.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: boundary loss; distance map; distance transform; loss function; Semantic segmentation
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Erchan Aptoula
Date Deposited: 05 Dec 2024 11:43
Last Modified: 05 Dec 2024 11:43
URI: https://research.sabanciuniv.edu/id/eprint/50490

Actions (login required)

View Item
View Item