SITS-Former: A pre-trained spatio-spectral-temporal representation model for Sentinel-2 time series classification
International Journal of Applied Earth Observation and Geoinformation(2022)
摘要
•We present SITS-Former, which is the first pre-trained representation model for patch-based Sentinel-2 time series classification.•SITS-Former is pre-trained on massive unlabeled Sentinel-2 time series to learn spatio-spectral-temporal features via a missing-data imputation proxy task based on self-supervised learning.•SITS-Former can adapt the learned features to an interested classification task through fine-tuning.•SITS-Former outperforms state-of-the-art approaches and yields a significant improvement over the purely supervised method.
更多查看译文
关键词
Pre-training,satellite image time series (SITS),Self-supervised learning,Sentinel-2,Transformer
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要