论文标题
半监督的新颖性检测与正则分歧的合奏
Semi-supervised novelty detection using ensembles with regularized disagreement
论文作者
论文摘要
深层神经网络即使从看不见的类别来预测样本也通常会具有很高的信心样本，而应该被标记以进行专家评估。当前的新颖性检测算法除非可以访问与这些新样本相似的标记数据，否则无法可靠地识别出如此近的OOD点。在本文中，我们为半监督新颖性检测（SSND）开发了一种新的基于合奏的程序，该程序成功利用了未标记的ID和新颖级别样本的混合物来实现良好的检测性能。特别是，我们仅使用早期停止正规化来展示如何仅在OOD数据上实现分歧。尽管我们证明了这一事实，但我们的广泛实验表明，对于更复杂的方案，它是正确的：我们的方法在标准图像数据集（SVHN/CIFAR-10/CIFAR-100）上的最先进的SSND方法胜过最先进的SSND方法，并且仅具有可忽略的计算成本增加。
Deep neural networks often predict samples with high confidence even when they come from unseen classes and should instead be flagged for expert evaluation. Current novelty detection algorithms cannot reliably identify such near OOD points unless they have access to labeled data that is similar to these novel samples. In this paper, we develop a new ensemble-based procedure for semi-supervised novelty detection (SSND) that successfully leverages a mixture of unlabeled ID and novel-class samples to achieve good detection performance. In particular, we show how to achieve disagreement only on OOD data using early stopping regularization. While we prove this fact for a simple data distribution, our extensive experiments suggest that it holds true for more complex scenarios: our approach significantly outperforms state-of-the-art SSND methods on standard image data sets (SVHN/CIFAR-10/CIFAR-100) and medical image data sets with only a negligible increase in computation cost.
