Extracting building footprints from remote sensing images has been attra...
Self-training has shown great potential in semi-supervised learning. Its...
Currently, due to the high scalability and global coverage of space
info...
Though image-level weakly supervised semantic segmentation (WSSS) has
ac...
In this paper, we propose a transformer based approach for visual ground...
Coarsely-labeled semantic segmentation annotations are easy to obtain, b...