Our MapAI approach: focusing on data pipeline and loss functions
Open Access
- 21 September 2022
- journal article
- research article
- Published by University of Oslo Library in Nordic Machine Intelligence
- Vol. 2 (3)
Abstract
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.Keywords
This publication has 6 references indexed in Scilit:
- MapAI: Precision in Building SegmentationNordic Machine Intelligence, 2022
- Test-time augmentation for deep learning-based cell segmentation on microscopy imagesScientific Reports, 2020
- Combo loss: Handling input and output imbalance in multi-organ segmentationComputerized Medical Imaging and Graphics, 2019
- Focal Loss for Dense Object Detection2017
- scikit-image: image processing in PythonPeerJ, 2014
- Morphometric analysis of white matter lesions in MR images: method and validationIEEE Transactions on Medical Imaging, 1994