# A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features

arXiv: https://arxiv.org/abs/2105.00967 · HTML: https://mlsanity.com/paper/2105.00967/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 80 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [The Importance of Skip Connections in Biomedical Image Segmentation](https://mlsanity.com/paper/1608.04117/) (2016)
- [Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions](https://mlsanity.com/paper/1711.08141/) (2017)
- [Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features](https://mlsanity.com/paper/1806.04659/) (2018)
- [Going Deeper with Contextual CNN for Hyperspectral Image Classification](https://mlsanity.com/paper/1604.03519/) (2016)
- [Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance](https://mlsanity.com/paper/1805.10407/) (2018)
- [Missing Data Reconstruction in Remote Sensing image with a Unified Spatial-Temporal-Spectral Deep Convolutional Neural Network](https://mlsanity.com/paper/1802.08369/) (2018)
- [Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors](https://mlsanity.com/paper/1810.05801/) (2018)
- [Smoothed Dilated Convolutions for Improved Dense Prediction](https://mlsanity.com/paper/1808.08931/) (2018)
- [Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network](https://mlsanity.com/paper/1703.09695/) (2017)
- [Convolutional Neural Networks for Multispectral Image Cloud Masking](https://mlsanity.com/paper/2012.05325/) (2020)

## Built on by (most cited first, 2 of 2)

- [EarthNets: Empowering AI in Earth Observation](https://mlsanity.com/paper/2210.04936/) (2022)
- [Weakly Supervised Cloud Detection Combining Spectral Features and Multi-Scale Deep Network](https://mlsanity.com/paper/2510.00654/) (2025)

## Abstract (arXiv)

Clouds are a very important factor in the availability of optical remote sensing images. Recently, deep learning-based cloud detection methods have surpassed classical methods based on rules and physical models of clouds. However, most of these deep models are very large which limits their applicability and explainability, while other models do not make use of the full spectral information in multi-spectral images such as Sentinel-2. In this paper, we propose a lightweight network for cloud detection, fusing multi-scale spectral and spatial features (CDFM3SF) and tailored for processing all spectral bands in Sentinel- 2A images. The proposed method consists of an encoder and a decoder. In the encoder, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features. Three novel components are designed: a mixed depth-wise separable convolution (MDSC) and a shared and dilated residual block (SDRB) to extract multi-scale spatial features, and a concatenation and sum (CS) operation to fuse multi-scale spectral and spatial features with little calculation and no additional parameters. The decoder of CD-FM3SF outputs three cloud masks at the same resolution as input bands to enhance the supervision information of small, middle and large clouds. To validate the performance of the proposed method, we manually labeled 36 Sentinel-2A scenes evenly distributed over mainland China. The experiment results demonstrate that CD-FM3SF outperforms traditional cloud detection methods and state-of-theart deep learning-based methods in both accuracy and speed.