Diversified Multi-prototype Representation for Semi-supervised Segmentation
arXiv:2111.08651
Abstract
This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class with multiple prototypes. To avoid degenerate solutions, two regularization strategies are applied on unlabeled images. The first one leverages mutual information maximization to ensure that all prototype vectors are considered by the network. The second explicitly enforces prototypes to be orthogonal by minimizing their cosine distance. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.
References in corpus (9)
- Prototypical Networks for Few-shot Learning
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
- Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images
- Learning Discrete Representations via Information Maximizing Self-Augmented Training
- Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations
- Self-paced and self-consistent co-training for semi-supervised image segmentation
- Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training
- Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation
- Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels