-
SML: Semantic Meta-Learning for Few-shot Semantic Segmentation
The proposed Semantic Meta-Learning (SML) framework for few-shot semantic segmentation. -
Prototype Reļ¬nement Network for Few-Shot Segmentation
Few-shot segmentation targets to segment new classes with few annotated images provided. It is more challenging than traditional semantic segmentation tasks that segment known... -
Few-shot semantic segmentation via prototype augmentation with image-level an...
Few-shot semantic segmentation via prototype augmentation with image-level annotations