Skip to main content Skip to main navigation


Location-Specific Embedding Learning for the Semantic Segmentation of Building Footprints on a global scale

Benjamin Bischke; Patrick Helber; Jörn Hees; Andreas Dengel
In: Global-Environment Observation and Disaster Mitigation. IEEE International Geoscience and Remote Sensing Symposium (IGARSS-2019), July 28 - August 2, Yokohama, Japan, IEEE, 2019.


In this paper, we analyze the feasibility of learning a latent embedding space from aerial and satellite imagery in order to capture semantic properties of geographical locations. We show that deep neural network, trained with a triplet loss function, can be effectively used to obtain a location-specific embedding. Considering the problem of building footprint segmentation from aerial imagery of varying cities, we leverage these embeddings together with a clustering for the training of location-specific segmentation networks and the selection of the corresponding segmentation network during inference time. We evaluate our approach on the large-scale Inria Aerial Image Labeling Dataset which contains aerial images of globally distributed cities. Our approach achieves an outperformance against state-of-the-art approaches on the Intersection over Union metric for the building class over all cities and by more than 2% for specific cities.