Noisy Supervision for Correcting Misaligned Cadaster Maps Without Perfect Ground Truth Data
This addresses the challenge of noisy labels in remote sensing for cadaster map alignment, offering a practical solution where perfect ground truth is unavailable.
The paper tackles the problem of aligning cadaster maps using noisy supervision from misaligned polygon annotations, and demonstrates that a multiple-round training scheme can iteratively correct annotations and improve alignment performance.
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 mis-aligned 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 reduce the noise of the dataset by iteratively training a better alignment model to correct the annotation alignment.