SemiSAM-O1 narrows the gap to fully supervised medical image segmentation performance while using only a single annotated template image through foundation-model feature propagation and uncertainty-guided iterative refinement.
arXiv preprint arXiv:2306.06370 (2023)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3roles
background 1polarities
background 1representative citing papers
RobustMedSAM fuses MedSAM's image encoder with RobustSAM's mask decoder and fine-tunes only the decoder on 35 medical datasets with corruptions to raise degraded-image Dice from 0.613 to 0.719.
A survey that reviews efficient variants of the Segment Anything Model, categorizes acceleration strategies, and provides a unified hardware evaluation on benchmarks.
citing papers explorer
-
SemiSAM-O1: How far can we push the boundary of annotation-efficient medical image segmentation?
SemiSAM-O1 narrows the gap to fully supervised medical image segmentation performance while using only a single annotated template image through foundation-model feature propagation and uncertainty-guided iterative refinement.
-
RobustMedSAM: Degradation-Resilient Medical Image Segmentation via Robust Foundation Model Adaptation
RobustMedSAM fuses MedSAM's image encoder with RobustSAM's mask decoder and fine-tunes only the decoder on 35 medical datasets with corruptions to raise degraded-image Dice from 0.613 to 0.719.
-
On Efficient Variants of Segment Anything Model: A Survey
A survey that reviews efficient variants of the Segment Anything Model, categorizes acceleration strategies, and provides a unified hardware evaluation on benchmarks.