PEMMA adapts a CT-only transformer segmentation model to CT+PET with LoRA/DoRA, reaching early-fusion-level Dice while training only 0.5-8% of parameters, and extends the same adapters to prognosis.
Parameter- efficient fine-tuning of large pretrained models for instance segmen- tation tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Parameter Adaptation for Multi-Modal Medical Image Segmentation and Prognosis
PEMMA adapts a CT-only transformer segmentation model to CT+PET with LoRA/DoRA, reaching early-fusion-level Dice while training only 0.5-8% of parameters, and extends the same adapters to prognosis.