PROTON is a test-time online OOD detection module for medical VLMs that maintains a prototype bank from confident predictions and adaptively combines prototype distance with MCM scoring via variance statistics, improving AUROC across covariate, semantic, and far-OOD shifts on FLAIR+FIVES without tra
Ultra-light test-time adaptation for Vision–Language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Semantic-Fast-SAM matches prior SAM-based semantic segmentation accuracy on Cityscapes and ADE20K while running about 20 times faster by combining FastSAM with SSA labeling and CLIP for open-vocabulary cases.
citing papers explorer
-
PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMs
PROTON is a test-time online OOD detection module for medical VLMs that maintains a prototype bank from confident predictions and adaptively combines prototype distance with MCM scoring via variance statistics, improving AUROC across covariate, semantic, and far-OOD shifts on FLAIR+FIVES without tra
-
Semantic-Fast-SAM: Efficient Semantic Segmenter
Semantic-Fast-SAM matches prior SAM-based semantic segmentation accuracy on Cityscapes and ADE20K while running about 20 times faster by combining FastSAM with SSA labeling and CLIP for open-vocabulary cases.