ASAP uses a multi-armed bandit to dynamically select auxiliary datasets during few-shot fine-tuning of medical segmentation foundation models, reporting improved Dice scores over existing methods.
Ethical approval was not required as confirmed by the license attached with the open access data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Adapting Foundation Models for Few-Shot Medical Image Segmentation: Actively and Sequentially
ASAP uses a multi-armed bandit to dynamically select auxiliary datasets during few-shot fine-tuning of medical segmentation foundation models, reporting improved Dice scores over existing methods.