A Miniaturized Semantic Segmentation Method for Remote Sensing Image
This work addresses memory efficiency for remote sensing applications, but it is incremental as it builds on standard U-Net with optimizations.
The authors tackled the problem of high memory usage in remote sensing image semantic segmentation by proposing a miniaturized neural network method, achieving 29.26 times model compression while maintaining performance on a public dataset.
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