Sequential fine-tuning with similarity-based data buffering and LoRA knowledge distillation improves 3D medical segmentation over parallel and multi-task fine-tuning.
Uniseg: A prompt-driven universal segmentation model as well as a strong representation learner,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation
Sequential fine-tuning with similarity-based data buffering and LoRA knowledge distillation improves 3D medical segmentation over parallel and multi-task fine-tuning.