A Miniaturized Semantic Segmentation Method for Remote Sensing Image
arXiv:1810.11603
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
arXiv comment5 pages, 3 figures, 3 tables, this paper is to be submitted to the conference
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
- Fully Convolutional Neural Networks for Crowd Segmentation