Uncertainty-aware semi-supervised few shot segmentation

Soopil Kim, Philip Chikontwe, Sion An, Sanghyun Park

Abstract: Highlights•We propose a new semi-supervised few-shot segmentation (FSS) method that employs additional prototypes from unlabeled images.•Our approach can be trained without an additional learning process for unlabeled samples.•We propose a novel uncertainty estimation method for prototype-based FSS.•Our method can reliably quantify uncertainty without degrading the baseline performance of existing FSS models.•Our method shows significant improvement over two baseline methods on two FSS benchmarks, i.e., PASCAL-5i and COCO-20i.