Estimating Uncertainty in Landslide Segmentation Models

arXiv:2311.11138v2 Announce Type: replace
Abstract: Landslides are a recurring, widespread hazard. Preparation and mitigation efforts can be aided by a high-quality, large-scale dataset that covers global at-risk areas. Such a dataset currently does not exist and is impossible to construct manually. Recent automated efforts focus on deep learning models for landslide segmentation (pixel labeling) from satellite imagery. However, it is also important to characterize the uncertainty or confidence levels of such segmentations. Accurate and robust uncertainty estimates can enable low-cost …

abstract arxiv automated construct cs.cv dataset deep learning focus global labeling pixel quality risk scale segmentation type uncertainty