Search Results for author:
Found 2 papers, 1 papers with code
A simple, strong baseline for building damage detection on the xBD dataset
We construct a strong baseline method for building damage detection by starting with the highly-engineered winning solution of the xView2 competition, and gradually stripping away components.
Contrastive pretraining for semantic segmentation is robust to noisy positive pairs
Domain-specific variants of contrastive learning can construct positive pairs from two distinct in-domain images, while traditional methods just augment the same image twice.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
