Curates over 900 hours of SRKW acoustic data plus other marine mammal recordings via positive-unlabeled active learning, releasing transformer classifiers that report AUROC 0.58-0.77 and species top-1 accuracy of 53.2% on held-out benchmarks.
Daniel M Kane, Ilias Diakonikolas, Hanshen Xiao, and Sihan Liu
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Non-asymptotic analysis of prediction-powered mean estimation shows that no-regret learning for query probabilities converges to the maximum allowed constant value, independent of covariates.
citing papers explorer
-
Positive-Unlabelled Active Learning to Curate a Dataset for Orca Resident Interpretation
Curates over 900 hours of SRKW acoustic data plus other marine mammal recordings via positive-unlabeled active learning, releasing transformer classifiers that report AUROC 0.58-0.77 and species top-1 accuracy of 53.2% on held-out benchmarks.
-
Revisiting Active Sequential Prediction-Powered Mean Estimation
Non-asymptotic analysis of prediction-powered mean estimation shows that no-regret learning for query probabilities converges to the maximum allowed constant value, independent of covariates.