XSSR selects 5% of target samples via source-trained MAE embeddings and auto-calibrated greedy scoring to reach 99.3% of full-data Dice on chest X-ray and outperform random/CoreSet baselines on retinal and prostate MRI benchmarks.
arXiv preprint arXiv:2002.03366 (2020)
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
-
XSSR: Cross-Domain Self-Supervised Representative Selection for Efficient Annotation in Medical Image Segmentation
XSSR selects 5% of target samples via source-trained MAE embeddings and auto-calibrated greedy scoring to reach 99.3% of full-data Dice on chest X-ray and outperform random/CoreSet baselines on retinal and prostate MRI benchmarks.