Building extraction from remote sensing (RS) images is a fundamental task for geospatial
applications, aiming to obtain morphology, location, and other information about buildings …

The annotations used during the training process are crucial for the inference results of
remote sensing images (RSIs) based on a deep learning framework. Unlabeled RSIs can be …

Extracting buildings accurately from very high-resolution (VHR) remote sensing imagery is
challenging due to diverse building appearances, spectral variability, and complex …

Remote sensing building extraction is of great importance to many applications, such as
urban planning and economic status assessment. Deep learning with deep network …

Applying deep-learning methods, especially fully convolutional networks (FCNs), has
become a popular option for land-cover classification or segmentation in remote sensing …

As one of the most important types of artificial ground features, building images and outlines
are widely used in map updating, GIS analysis, urban planning, and environmental …

Using deep learning in remote sensing interpretation could reduce a lot of human and
material costs. Semantic segmentation is the main method for this task. It can automatically …

Benefiting from the high coverage and re-visiting frequency, the satellite imagery is an ideal
data for large-scale, real-time earth observation. However, due to the limited resolution and …

To extract information at scale, researchers are increasingly applying semantic
segmentation techniques to remotely-sensed imagery. While fully-supervised learning …

Semantic segmentation could not distinguish the spot's contour, which has both the
construction disturbance region and original physiognomy. This paper proposed a semantic …