A Multi-Task Deep Learning Framework for Building Footprint Segmentation
This work addresses the problem of poorly classified segmentation maps in remote sensing for applications like urban planning, but it is incremental as it builds on existing multi-task learning approaches.
The authors tackled building footprint segmentation in remote sensing by proposing a multi-task deep learning framework that jointly optimizes delineation with auxiliary tasks like image reconstruction and boundary segmentation, resulting in considerable accuracy improvements on the SpaceNet6 dataset compared to single-task models.
The task of building footprint segmentation has been well-studied in the context of remote sensing (RS) as it provides valuable information in many aspects, however, difficulties brought by the nature of RS images such as variations in the spatial arrangements and in-consistent constructional patterns require studying further, since it often causes poorly classified segmentation maps. We address this need by designing a joint optimization scheme for the task of building footprint delineation and introducing two auxiliary tasks; image reconstruction and building footprint boundary segmentation with the intent to reveal the common underlying structure to advance the classification accuracy of a single task model under the favor of auxiliary tasks. In particular, we propose a deep multi-task learning (MTL) based unified fully convolutional framework which operates in an end-to-end manner by making use of joint loss function with learnable loss weights considering the homoscedastic uncertainty of each task loss. Experimental results conducted on the SpaceNet6 dataset demonstrate the potential of the proposed MTL framework as it improves the classification accuracy considerably compared to single-task and lesser compounded tasks.