A semi-supervised framework distills vision foundation models into compact instance segmentation experts that outperform their teachers by up to 11.9 AP on Cityscapes and 8.6 AP on ADE20K while being 11 times smaller.
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.Advances in neural information processing systems, 30
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
SemiGDA aligns feature and semantic distributions via dual encoders and skip adapters to boost semi-supervised medical image segmentation.
UniSemAlign aligns text and prototype representations with visual features to generate better supervision signals for semi-supervised segmentation, reporting Dice gains of up to 8.6% on CRAG with 10% labels.
A multi-teacher collaborative framework with reliability assessment for forward-looking sonar semantic segmentation reports 5.08% mIoU gain on FLSMD dataset using only 2% labeled data.
citing papers explorer
-
Training a Student Expert via Semi-Supervised Foundation Model Distillation
A semi-supervised framework distills vision foundation models into compact instance segmentation experts that outperform their teachers by up to 11.9 AP on Cityscapes and 8.6 AP on ADE20K while being 11 times smaller.
-
SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation
SemiGDA aligns feature and semantic distributions via dual encoders and skip adapters to boost semi-supervised medical image segmentation.
-
UniSemAlign: Text-Prototype Alignment with a Foundation Encoder for Semi-Supervised Histopathology Segmentation
UniSemAlign aligns text and prototype representations with visual features to generate better supervision signals for semi-supervised segmentation, reporting Dice gains of up to 8.6% on CRAG with 10% labels.
-
CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels
A multi-teacher collaborative framework with reliability assessment for forward-looking sonar semantic segmentation reports 5.08% mIoU gain on FLSMD dataset using only 2% labeled data.