Diversified Multi-prototype Representation for Semi-supervised Segmentation

2021/11/16 by Jizong Peng, Christian Desrosiers, Peng, Jizong +3 · 1 citation
Computer Science · Mathematics · #Advanced Neural Network Applications #Artificial intelligence #Benchmark (surveying) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Image segmentation #Machine learning #Mathematical optimization #Mathematics #Maximization #Medical Image Segmentation Techniques #Pattern recognition (psychology) #Regularization (linguistics) #Representation (politics) #Scale-space segmentation #Segmentation #cs.CV

paper · pdf · doi:10.48550/arxiv.2111.08651

published in arXiv (Cornell University) (Cornell University)

arxiv created 2021/11/16 · openalex publication_date 2021/11/16 · arxiv updated 2021/11/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

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.

Citations

• Prototypical Networks for Few-shot Learning
• Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Deep co-training for semi-supervised image segmentation
• Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation

Related

• Mixed Prototype Consistency Learning for Semi-supervised Medical Image Segmentation
• Multi-Prototype Embedding Refinement for Semi-Supervised Medical Image Segmentation
• Efficient Prototype Consistency Learning in Medical Image Segmentation via Joint Uncertainty and Data Augmentation
• Mutual- and Self- Prototype Alignment for Semi-supervised Medical Image Segmentation
• Mutual Consistency Learning for Semi-supervised Medical Image Segmentation