Robust Deep Active Learning via Distance-Measured Data Mixing and Adversarial Training
Sign Up to like & getrecommendations! Published in 2025 at "Entropy"
DOI: 10.3390/e27111159
Abstract: Accurate uncertainty estimation in unlabeled data represents a fundamental challenge in active learning. Traditional deep active learning approaches suffer from a critical limitation: uncertainty-based selection strategies tend to concentrate excessively around noisy decision boundaries, while… read more here.
Keywords: deep active; distance measured; measured data; active learning ... See more keywords