Our MapAI approach: focusing on data pipeline and loss functions
Nordic Machine Intelligence · 2023
DOI: 10.5617/nmi.10161 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nordic Machine Intelligence, 2023. Verfasst von Tord Kriznik Sørensen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Precision building detection is a difficult challenge because resolution, lighting conditions, and image quality greatly influence the performance of machine learning models. Additionally, the building types, settlement structure, road structure, soil color and texture, vegetation, and car types can also affect image segmentation, making the solutions local or regional. In this paper, we describe the solution for the MapAI challenge submitted by the ATELIER team. We focused on two primary parts: data processing and loss functions. Our main insights were that the data can be effectively resampled by exploiting its structure and that the boundary intersection over union metric is very forgiving, not giving the network enough incentive to refine the borders. The segmentation was performed with a standard 5-level deep U-Net with an additional conditional random fields (CRF) denoiser.
Zitieren
APA
Sørensen, T. K., Vermeer, M., Hay, J. A., Fantin, D., & Völgyes, D. (2023). Our MapAI approach: focusing on data pipeline and loss functions. Nordic Machine Intelligence. https://doi.org/10.5617/nmi.10161
Vancouver
Sørensen TK, Vermeer M, Hay JA, Fantin D, Völgyes D. Our MapAI approach: focusing on data pipeline and loss functions. Nordic Machine Intelligence. 2023. doi:10.5617/nmi.10161
BibTeX
@article{Srensen2023,
author = {Sørensen, Tord Kriznik and Vermeer, Martijn and Hay, Jacob Alexander and Fantin, Daniele and Völgyes, David},
title = {Our MapAI approach: focusing on data pipeline and loss functions},
journal = {Nordic Machine Intelligence},
year = {2023},
doi = {10.5617/nmi.10161}
}
EUVIMED