Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning

arXiv:2303.12091v3 Announce Type: replace
Abstract: Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers). Most previous works focused on outlier detection via binary classifiers, which suffer from insufficient scalability and inability to distinguish different types of uncertainty. In this paper, we propose a novel framework, …

abstract arxiv cs.ai cs.cv cs.lg data deep learning distribution negative outliers practical semi-supervised semi-supervised learning set ssl supervised learning test type