ECDNet: A bilateral lightweight cloud detection network for remote sensing images

作者：

Highlights：

• We propose a neural network: ECDNet. It consists of a lightweight two-pathway encoder and an extremely lightweight decoder.

• In the encoder, the dense pyramid module (DPM) is designed to have large and diverse receptive fields in feature extraction.

• In the encoder, the fusion module (FM) is developed to fuse detail and semantic information more efficiently.

• The experiment results on LandSat8 and MODIS demonstrate that ECDNet can achieve state-of-the-art performance.

摘要

•We propose a neural network: ECDNet. It consists of a lightweight two-pathway encoder and an extremely lightweight decoder.•In the encoder, the dense pyramid module (DPM) is designed to have large and diverse receptive fields in feature extraction.•In the encoder, the fusion module (FM) is developed to fuse detail and semantic information more efficiently.•The experiment results on LandSat8 and MODIS demonstrate that ECDNet can achieve state-of-the-art performance.

论文关键词：Lightweight network,Efficient cloud detection,Dual-branch architecture

论文评审过程：Received 29 September 2021, Revised 4 March 2022, Accepted 13 April 2022, Available online 14 April 2022, Version of Record 1 May 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108713