Overcoming Missing and Incomplete Modalities with Generative Adversarial Networks for Building Footprint Segmentation
This addresses a practical limitation in remote sensing applications where data collection often results in incomplete modalities, though it is incremental as it builds on existing multi-modal fusion methods.
The paper tackles the problem of missing or incomplete modalities in multi-modal remote sensing data for building footprint segmentation, achieving about a 2% improvement in Intersection over Union (IoU) compared to using only available modalities.
The integration of information acquired with different modalities, spatial resolution and spectral bands has shown to improve predictive accuracies. Data fusion is therefore one of the key challenges in remote sensing. Most prior work focusing on multi-modal fusion, assumes that modalities are always available during inference. This assumption limits the applications of multi-modal models since in practice the data collection process is likely to generate data with missing, incomplete or corrupted modalities. In this paper, we show that Generative Adversarial Networks can be effectively used to overcome the problems that arise when modalities are missing or incomplete. Focusing on semantic segmentation of building footprints with missing modalities, our approach achieves an improvement of about 2% on the Intersection over Union (IoU) against the same network that relies only on the available modality.