FSAM integrates a frequency adapter into SAM with LoRA to extract domain-invariant high-frequency features and outperforms prior domain generalization methods on fundus and prostate datasets.
IEEE Transactions on Medical Imaging42(4), 1095–1106 (2022)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
Targeted data augmentations let single-sequence 3D spine segmentation models generalize to seven unseen CT and MRI datasets with 155% average Dice gain and almost no in-domain loss.
citing papers explorer
-
Frequency Adapter with SAM for Generalized Medical Image Segmentation
FSAM integrates a frequency adapter into SAM with LoRA to extract domain-invariant high-frequency features and outperforms prior domain generalization methods on fundus and prostate datasets.
-
One Sequence to Segment Them All: Efficient Data Augmentation for CT and MRI Cross-Domain 3D Spine Segmentation
Targeted data augmentations let single-sequence 3D spine segmentation models generalize to seven unseen CT and MRI datasets with 155% average Dice gain and almost no in-domain loss.