Feature Pyramid Network for Multi-Class Land Segmentation
Abstract
Semantic segmentation is in-demand in satellite imagery processing. Because of the complex environment, automatic categorization and segmentation of land cover is a challenging problem. Solving it can help to overcome many obstacles in urban planning, environmental engineering or natural landscape monitoring. In this paper, we propose an approach for automatic multi-class land segmentation based on a fully convolutional neural network of feature pyramid network (FPN) family. This network is consisted of pre-trained on ImageNet Resnet50 encoder and neatly developed decoder. Based on validation results, leaderboard score and our own experience this network shows reliable results for the DEEPGLOBE - CVPR 2018 land cover classification sub-challenge. Moreover, this network moderately uses memory that allows using GTX 1080 or 1080 TI video cards to perform whole training and makes pretty fast predictions.
Cite
Text
Seferbekov et al. "Feature Pyramid Network for Multi-Class Land Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00051Markdown
[Seferbekov et al. "Feature Pyramid Network for Multi-Class Land Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/seferbekov2018cvprw-feature/) doi:10.1109/CVPRW.2018.00051BibTeX
@inproceedings{seferbekov2018cvprw-feature,
title = {{Feature Pyramid Network for Multi-Class Land Segmentation}},
author = {Seferbekov, Selim S. and Iglovikov, Vladimir and Buslaev, Alexander and Shvets, Alexey},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2018},
pages = {272-275},
doi = {10.1109/CVPRW.2018.00051},
url = {https://mlanthology.org/cvprw/2018/seferbekov2018cvprw-feature/}
}