MedVeriSeg is a training-free framework that analyzes similarity maps from the [SEG] token and uses GPT-4o to verify whether a segmentation query targets an object actually present in a medical image.
Title resolution pending
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
-
MedVeriSeg: Teaching MLLM-Based Medical Segmentation Models to Verify Query Validity Without Extra Training
MedVeriSeg is a training-free framework that analyzes similarity maps from the [SEG] token and uses GPT-4o to verify whether a segmentation query targets an object actually present in a medical image.