Noisy Supervision for Correcting Misaligned Cadaster Maps Without Perfect Ground Truth Data

ABSTRACT In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available. However, labels are often noisy, especially in remote sensing where manually curated public datasets are rare. We study the multi-modal cadaster map alignment problem for which available annotations are misaligned polygons, resulting in noisy supervision. We subsequently set up a multiple-rounds training scheme which corrects the ground truth annotations at each round to better train the model at the next round. We show that it is possible to Figure 1: Qualitative alignment results on a crop of an image of reduce the noise of the dataset by iteratively training a better Bloomington from the Inria dataset.