Land Cover Classification from Remote Sensing Images Based on Multi-Scale Fully Convolutional Network

This addresses land cover classification for remote sensing applications, but appears incremental as it builds on existing fully convolutional network methods.

The paper tackled land cover classification from remote sensing images by proposing a Multi-Scale Fully Convolutional Network (MSFCN) with multi-scale convolutional kernels, but no concrete results or numbers were provided in the abstract.