期刊名称:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN:2194-9042
电子版ISSN:2194-9050
出版年度:2022
卷号:V-3-2022
页码:17-23
DOI:10.5194/isprs-annals-V-3-2022-17-2022
语种:English
出版社:Copernicus Publications
摘要:Neural architecture search (NAS) is a subset of automated machine learning that tries to find the best neural network to perform a given task. In this article, a network search space is defined and applied to perform the semantic segmentation of satellite imagery. Due to the spatial nature of the data, the search space uses cells that group parallel operations with kernels of different sizes, providing options to accommodate the neighborhood information required to perform a better classification. The architecture search space follows a UNet-like network. The proposed approach uses scaled sigmoid gates, a strategy for network pruning that was adapted to search for the best operations on the cell search space. The architecture achieved by the proposed approach uses wider kernels on lower resolution feature maps, which leads to the interpretation that some pixels required information from pixels farther away than expected. The resulting network was compared to a very similar UNet-like network that only used 3×3 convolutions. The resulting network shows slightly better results on the test set.