MPCL uses intensity-aligned heterogeneous prototype generation, prototypical space optimization, and dual-branch knowledge alignment to improve semi-supervised medical image segmentation by modeling intra-class heterogeneity.
All-around reallabelsupervision:Cyclicprototypeconsistencylearningforsemi- supervisedmedicalimagesegmentation.IEEEJournalofBiomedical and Health Informatics, 26(7):3174–3184, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Embracing Intra-Class Heterogeneity for Semi-Supervised Medical Image Segmentation: From Diversity to Precision
MPCL uses intensity-aligned heterogeneous prototype generation, prototypical space optimization, and dual-branch knowledge alignment to improve semi-supervised medical image segmentation by modeling intra-class heterogeneity.