Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks
This addresses a domain-specific challenge in remote sensing for applications like urban planning, but it is incremental as it builds on existing deep learning segmentation methods.
The paper tackles the problem of poor boundary preservation in semantic segmentation of high-resolution satellite imagery by introducing a cascaded multi-task loss, achieving an 8.3% improvement over state-of-the-art methods without post-processing.
The increased availability of high resolution satellite imagery allows to sense very detailed structures on the surface of our planet. Access to such information opens up new directions in the analysis of remote sensing imagery. However, at the same time this raises a set of new challenges for existing pixel-based prediction methods, such as semantic segmentation approaches. While deep neural networks have achieved significant advances in the semantic segmentation of high resolution images in the past, most of the existing approaches tend to produce predictions with poor boundaries. In this paper, we address the problem of preserving semantic segmentation boundaries in high resolution satellite imagery by introducing a new cascaded multi-task loss. We evaluate our approach on Inria Aerial Image Labeling Dataset which contains large-scale and high resolution images. Our results show that we are able to outperform state-of-the-art methods by 8.3\% without any additional post-processing step.