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, 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.

翻译：半监督学习（SSL）方法假设标记数据、未标记数据和测试数据来自同一分布。开放集半监督学习（Open-set SSL）考虑了更实际的场景，其中未标记数据和测试数据包含未在标记数据（内点）中出现的新类别（外点）。以往大多数研究通过二元分类器进行外点检测，但这类方法存在可扩展性不足且无法区分不同类型不确定性的缺陷。本文提出一种新型框架——自适应负证据深度学习（ANEDL）以解决上述局限性。具体而言，我们首先引入证据深度学习（EDL）作为外点检测器来量化不同类型的不确定性，并针对自训练和推理过程设计不同的不确定性度量指标。此外，我们提出一种新颖的自适应负优化策略，使EDL更适用于同时包含内点和外点的未标记数据集。实验结果表明，我们的方法在四个数据集上的性能均优于现有最先进方法。