摘要
Deep learning has achieved great success in learning features from massive remote sensing images (RSIs). To better understand the connection between three feature learning paradigms, which are unsupervised feature learning (USFL), supervised feature learning (SFL), and self-SFL (SSFL), this article analyzes and compares them from the perspective of feature learning signals and gives a unified feature learning framework. Under this unified framework, we analyze the advantages of SSFL over the other two learning paradigms in RSI understanding tasks and give a comprehensive review of existing SSFL works in RS, including the pretraining dataset, SSFL signals, and evaluation methods. We further analyze the effects of SSFL signals and pretraining data on the learned features to provide insights into RSI feature learning. Finally, we briefly discuss some open problems and possible research directions.
学科与关键词
- Remote Sensing Image Scene Classification with Self-Supervised Learning Based on Partially Unlabeled DatasetsChen, Xiliang; Zhu, Guobin*; Liu, MingqingRemote Sensing, 2022, 14(22): 5838.被引 10
- Beyond Supervised Learning in Remote Sensing: A Systematic Review of Deep Learning ApproachesHosseiny, Benyamin; Mahdianpari, Masoud*; Hemati, Mohammadali; Radman, Ali; Mohammadimanesh, Fariba; Chanussot, JocelynIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 1035-1052.被引 13
- Special focus on deep learning in remote sensing image processingFeng, Xu; Cheng, Hu; Jun, Li; Antonio, Plaza; Mihai, DatcuScience China Information Sciences, 2020, 63(4): 140300.被引 4
