Self-Attentive Generative Adversarial Network for Cloud Detection in High Resolution Remote Sensing Images

Zhaocong Wu, Jun Li, Yisong Wang, Zhongwen Hu, Matthieu Molinier

Research output: Contribution to journalArticleScientificpeer-review

14 Citations (Scopus)

Abstract

Cloud detection is an important step in the processing of remote sensing images. Most methods based on convolutional neural networks (CNNs) for cloud detection require pixel-level labels, which are time-consuming and expensive to annotate. To overcome this challenge, this letter proposes a novel semisupervised algorithm for cloud detection by training a self-attentive generative adversarial network (SAGAN) to extract the feature difference between cloud images and cloud-free images. Our main idea is to introduce visual attention into the process of generating 'real' cloud-free images. The training of SAGAN is based on three guiding principles: expansion of attention maps of cloud regions which will be replaced with translated cloud-free images, reduction of attention maps to coincide with cloud boundaries, and optimization of a self-attentive network to handle the extreme cases. The inputs for SAGAN training are the images and image-level labels, which are easier, cheaper, and more time-saving than the existing methods based on CNN. To test the performance of SAGAN, experiments are conducted on the Sentinel-2A Level 1C image data. The results show that the proposed method achieves very promising results with only the image-level labels of training samples.

Original languageEnglish
Article number8924781
Pages (from-to)1792-1796
JournalIEEE Geoscience and Remote Sensing Letters
Volume17
Issue number10
DOIs
Publication statusPublished - Oct 2020
MoE publication typeA1 Journal article-refereed

Keywords

  • Cloud detection
  • deep learning (DL)
  • generative adversarial network (GAN)
  • remote sensing
  • self-attention

Fingerprint

Dive into the research topics of 'Self-Attentive Generative Adversarial Network for Cloud Detection in High Resolution Remote Sensing Images'. Together they form a unique fingerprint.

Cite this