Disentangling the Benefits of Self-Supervised Learning to Deployment-Driven Downstream Tasks of Satellite Images (Student Abstract)
Abstract
In this paper, we investigate the benefits of self-supervised learning (SSL) to downstream tasks of satellite images. Unlike common student academic projects, this work focuses on the advantages of the SSL for deployment-driven tasks which have specific scenarios with low or high-spatial resolution images. Our preliminary experiments demonstrate the robust benefits of the SSL trained by medium-resolution (10m) images to both low-resolution (100m) scene classification case (4.25%↑) and very high-resolution (5cm) aerial image segmentation case (1.96%↑), respectively.
Cite
Text
Deng et al. "Disentangling the Benefits of Self-Supervised Learning to Deployment-Driven Downstream Tasks of Satellite Images (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26959Markdown
[Deng et al. "Disentangling the Benefits of Self-Supervised Learning to Deployment-Driven Downstream Tasks of Satellite Images (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/deng2023aaai-disentangling/) doi:10.1609/AAAI.V37I13.26959BibTeX
@inproceedings{deng2023aaai-disentangling,
title = {{Disentangling the Benefits of Self-Supervised Learning to Deployment-Driven Downstream Tasks of Satellite Images (Student Abstract)}},
author = {Deng, Zhuo and Wei, Yibing and Zhu, Mingye and Wang, Xueliang and Zhou, Junchi and Yang, Zhicheng and Zhou, Hang and Cao, Zhenjie and Ma, Lan and Han, Mei and Lai, Jui-Hsin},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2023},
pages = {16198-16199},
doi = {10.1609/AAAI.V37I13.26959},
url = {https://mlanthology.org/aaai/2023/deng2023aaai-disentangling/}
}