A Miniaturized Semantic Segmentation Method for Remote Sensing Image

TL;DR

This paper introduces Micro-Net, a compact neural network for remote sensing image segmentation that significantly reduces model size while maintaining performance, enabling efficient processing on limited hardware.

Contribution

The paper presents a novel miniaturization approach for U-Net tailored to remote sensing images, combining compact convolution optimization and improved cascade atrous convolution.

Findings

29.26 times model compression achieved

Performance remains stable after miniaturization

Open-source implementation provided

Abstract

In order to save the memory, we propose a miniaturization method for neural network to reduce the parameter quantity existed in remote sensing (RS) image semantic segmentation model. The compact convolution optimization method is first used for standard U-Net to reduce the weights quantity. With the purpose of decreasing model performance loss caused by miniaturization and based on the characteristics of remote sensing image, fewer down-samplings and improved cascade atrous convolution are then used to improve the performance of the miniaturized U-Net. Compared with U-Net, our proposed Micro-Net not only achieves 29.26 times model compression, but also basically maintains the performance unchanged on the public dataset. We provide a Keras and Tensorflow hybrid programming implementation for our model: https://github.com/Isnot2bad/Micro-Net