Uncertainty guided semi-supervised few-shot segmentation with prototype level fusion

Hailing Wang, Chunwei Wu, Hai Zhang, Guitao Cao, Wenming Cao

Abstract: Highlights•Propose a novel semi-supervised method to address spatial inconsistency.•Introduce uncertainty-guided pseudo-labeling denoising.•Design a prototype-level fusion strategy to improve confusion regions prediction.•Explore the effectiveness of our method on PASCAL-5i and COCO-20i datasets.