Deep Aggregation Net for Land Cover Classification
Abstract
Land cover classification aims at classifying each pixel in a satellite image into a particular land cover category, which can be regarded as a multi-class semantic segmentation task. In this paper, we propose a deep aggregation network for solving this task, which extracts and combines multi-layer features during the segmentation process. In particular, we introduce soft semantic labels and graph-based fine tuning in our proposed network for improving the segmentation performance. In our experiments, we demonstrate that our network performs favorably against state-of-the-art models on the dataset of DeepGlobe Satellite Challenge, while our ablation study further verifies the effectiveness of our proposed network architecture.
Cite
Text
Kuo et al. "Deep Aggregation Net for Land Cover Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00046Markdown
[Kuo et al. "Deep Aggregation Net for Land Cover Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/kuo2018cvprw-deep/) doi:10.1109/CVPRW.2018.00046BibTeX
@inproceedings{kuo2018cvprw-deep,
title = {{Deep Aggregation Net for Land Cover Classification}},
author = {Kuo, Tzu-Sheng and Tseng, Keng-Sen and Yan, Jia-Wei and Liu, Yen-Cheng and Wang, Yu-Chiang Frank},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2018},
pages = {252-256},
doi = {10.1109/CVPRW.2018.00046},
url = {https://mlanthology.org/cvprw/2018/kuo2018cvprw-deep/}
}