Cloud and snow detection, deep learning, generative adversarial networks (GANs), remote sensing images, weakly supervised learning, Ocean engineering, TC1501-1800, Geophysics. Cosmic physics, QC801-809

Cloud and snow detection in remote sensing images has advanced significantly with the aid of deep learning methods. However, deep learning methods necessitate a large quantity of labeled data, which consumes a substantial amount of human and material resources. Numerous studies have focused on weakly supervised methods to reduce the workload of annotation, but the majority of these methods concentrate on cloud detection and involve snow detection only infrequently. In this article, we propose a novel weakly supervised cloud and snow detection method. Under the guidance of the remote sensing imaging mechanism, we design generative adversarial networks (GANs) to generate cloud and snow images and pseudolabels for training detection networks. The proposed method can generate clouds of different states and reproduce snow's texture. For both the cloud GAN model and snow GAN model, with only image-level annotation training supervision, the models produce both pixel-level cloud/snow reflectance and cloud opacity to obtain the generated remote sensing images and corresponding pseudolabels. Compared to other weakly supervised methods, our method achieves superior cloud and snow detection performance.