ANEDL: Adaptive Negative Evidential Deep Learning for Open-Set Semi-supervised Learning
AAAI 2024(2024)
摘要
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) con-
siders 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 out-
lier 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,
Adaptive Negative Evidential Deep Learning (ANEDL) to
tackle these limitations. Concretely, we first introduce evidential deep learning (EDL) as an outlier detector to quantify
different types of uncertainty, and design different uncertainty
metrics for self-training and inference. Furthermore, we propose a novel adaptive negative optimization strategy, making
EDL more tailored to the unlabeled dataset containing both
inliers and outliers. As demonstrated empirically, our proposed method outperforms existing state-of-the-art methods
across four datasets.
更多查看译文
关键词
ML: Semi-Supervised Learning,ML: Calibration & Uncertainty Quantification
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要