Research map / Label-efficient and robust learning / Semi-supervised learning

Parametric Meets Non-parametric: Bridging Dual Prediction Spaces for Semi-supervised Medical Image Segmentation

NeurIPS 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical segmentation

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Bridges parametric network predictions and non-parametric prototype-based predictions to reduce pseudo-label noise in semi-supervised medical image segmentation.

Problem

Semi-supervised medical image segmentation relies on pseudo-labeling, which suffers from prediction noise, especially when supervision is scarce.

Approach

Observes that parametric network predictions and non-parametric prototype-based predictions behave complementarily under pseudo-label noise, and bridges the two dual prediction spaces to improve pseudo-labels.

Closest papers by meaning

• DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.89)
• SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.88)
• A Semantic Knowledge Complementarity based Decoupling Framework for Semi-supervised Class-imbalanced Medical Image Segmentation (CVPR 2025 · similarity 0.88)
• GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.88)
• DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.87)
• S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging (AAAI 2025 · similarity 0.87)