Semantic segmentation in large-scale aerial images is an extremely challenging task. On one hand, the limited ground truth, as compared to the vast area the images cover, greatly hinders the ...

Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is ...

Semantic segmentation is a fundamental but challenging problem of pixel-level remote sensing (RS) data analysis. Semantic segmentation tasks based on aerial and satellite images play an important role ...

Factorized convolution is commonly used in mobile and embedded deep learning applications where computational and memory resources are limited. It has been shown to be effective in a variety of ...

Much prior art was dedicated to domain-adaptive semantic segmentation in the synthetic-to-real context. Despite being a crucial output of the perception stack, panoptic segmentation has been largely ...

However, many of recent semantic segmentation works only consider class accuracy and ignore the accuracies at the boundaries between semantic classes. To improve the semantic boundary accuracy, we ...