DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation

TL;DR

DDUNet is a lightweight, dual dynamic U-Net architecture designed for highly-efficient cloud segmentation, addressing receptive field constraints, robustness, and parameter efficiency, achieving 95.3% accuracy with only 0.33M parameters.

Contribution

The paper introduces DDUNet, a novel dual dynamic U-Net with dynamic multi-scale convolution and weight generator modules for improved cloud segmentation.

Findings

Achieves 95.3% accuracy on SWINySEG dataset.

Uses only 0.33 million parameters, enabling real-time performance.

Outperforms existing methods in accuracy and efficiency.

Abstract

Cloud segmentation amounts to separating cloud pixels from non-cloud pixels in an image. Current deep learning methods for cloud segmentation suffer from three issues. (a) Constrain on their receptive field due to the fixed size of the convolution kernel. (b) Lack of robustness towards different scenarios. (c) Requirement of a large number of parameters and limitations for real-time implementation. To address these issues, we propose a Dual Dynamic U-Net (DDUNet) for supervised cloud segmentation. The DDUNet adheres to a U-Net architecture and integrates two crucial modules: the dynamic multi-scale convolution (DMSC), improving merging features under different reception fields, and the dynamic weights and bias generator (DWBG) in classification layers to enhance generalization ability. More importantly, owing to the use of depth-wise convolution, the DDUNet is a lightweight network that can achieve 95.3% accuracy on the SWINySEG dataset with only 0.33M parameters, and achieve superior performance over three different configurations of the SWINySEg dataset in both accuracy and efficiency.