High-Resolution Cloud Detection Network

TL;DR

This paper presents HR-cloud-Net, a high-resolution neural network architecture for cloud detection that captures detailed textures and improves accuracy through multi-resolution feature fusion and a teacher-student training scheme.

Contribution

It introduces a novel high-resolution integration architecture and a teacher-student training approach for enhanced cloud detection performance.

Findings

Outperforms existing cloud detection methods on multiple datasets

Effectively captures complex cloud textures at high resolutions

Improves robustness through noisy image augmentation and supervision

Abstract

The complexity of clouds, particularly in terms of texture detail at high resolutions, has not been well explored by most existing cloud detection networks. This paper introduces the High-Resolution Cloud Detection Network (HR-cloud-Net), which utilizes a hierarchical high-resolution integration approach. HR-cloud-Net integrates a high-resolution representation module, layer-wise cascaded feature fusion module, and multi-resolution pyramid pooling module to effectively capture complex cloud features. This architecture preserves detailed cloud texture information while facilitating feature exchange across different resolutions, thereby enhancing overall performance in cloud detection. Additionally, a novel approach is introduced wherein a student view, trained on noisy augmented images, is supervised by a teacher view processing normal images. This setup enables the student to learn from cleaner supervisions provided by the teacher, leading to improved performance. Extensive evaluations on three optical satellite image cloud detection datasets validate the superior performance of HR-cloud-Net compared to existing methods.The source code is available at \url{https://github.com/kunzhan/HR-cloud-Net}.