NAS-HRIS: Automatic Design and Architecture Search of Neural Network for Semantic Segmentation in Remote Sensing Images

Sensors

Wei Wei¹  Jingbo Lin²  Nengzhen Fang²  Weipeng Jing²  Mingwei Zhang²  Marcin Woźniak³  Robertas Damaševičius³ 

[1] College of Computer Science and Engineering, Xi’an University of Technology, Xi’an 710048, China;College of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, China;Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland;

关键词: deep learning;    high-resolution remote sensing;    image segmentation;    neural architecture search;    neural network optimisation;    urban monitoring;   

DOI  :  10.3390/s20185292

来源: DOAJ

【 摘 要 】

The segmentation of high-resolution (HR) remote sensing images is very important in modern society, especially in the fields of industry, agriculture and urban modelling. Through the neural network, the machine can effectively and accurately extract the surface feature information. However, using the traditional deep learning methods requires plentiful efforts in order to find a robust architecture. In this paper, we introduce a neural network architecture search (NAS) method, called NAS-HRIS, which can automatically search neural network architecture on the dataset. The proposed method embeds a directed acyclic graph (DAG) into the search space and designs the differentiable searching process, which enables it to learn an end-to-end searching rule by using gradient descent optimization. It uses the Gumbel-Max trick to provide an efficient way when drawing samples from a non-continuous probability distribution, and it improves the efficiency of searching and reduces the memory consumption. Compared with other NAS, NAS-HRIS consumes less GPU memory without reducing the accuracy, which corresponds to a large amount of HR remote sensing imagery data. We have carried out experiments on the WHUBuilding dataset and achieved 90.44% MIoU. In order to fully demonstrate the feasibility of the method, we made a new urban Beijing Building dataset, and conducted experiments on satellite images and non-single source images, achieving better results than SegNet, U-Net and Deeplab v3+ models, while the computational complexity of our network architecture is much smaller.

【 授权许可】

Unknown