MAE self-supervised pretraining of nnFormer yields higher Dice scores, faster convergence, and better generalization when labeled medical segmentation data is scarce.
MGFuseSeg: Attention-Guided Multi-Granularity Fusion for Medical Image Segmentation
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
-
MAE-Based Self-Supervised Pretraining for Data-Efficient Medical Image Segmentation Using nnFormer
MAE self-supervised pretraining of nnFormer yields higher Dice scores, faster convergence, and better generalization when labeled medical segmentation data is scarce.