FEEDS uses DINOv2 embeddings of PET maximum-intensity projections to select farthest unlabeled cases for annotation, matching fully-labeled training performance on AutoPET-III, DeepPSMA, and Dartmouth data with 70% less labeling.
Classification, staging and prognosis of lung cancer.European journal of radiology, 45(1):8–17, 2003
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Foundation Model-Enabled Efficient Data Sampling (FEEDS): A label-efficient training strategy for pan-cancer, multi-tracer PET/CT datasets
FEEDS uses DINOv2 embeddings of PET maximum-intensity projections to select farthest unlabeled cases for annotation, matching fully-labeled training performance on AutoPET-III, DeepPSMA, and Dartmouth data with 70% less labeling.