论文标题
IDECODE：共同分布检测的分布术
iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
论文作者
论文摘要
尽管它们在不同领域之间取得了成功，但诸如深度神经网络（DNN）之类的机器学习方法通常会产生不正确的预测，并对其训练分布以外的输入信心很高。 DNN在安全 - 关键领域中的部署需要检测到分布（OOD）数据，以便DNN可以弃权对这些数据进行预测。最近已经开发了许多方法以进行OOD检测，但是仍然有改进的余地。我们提出了新的方法IDEcode，利用了共形OOD检测的分配均值。它依赖于一种新型的基本非符合度度量和一种新的聚合方法，该方法用于电感保形异常检测框架，从而保证了有界的错误检测率。我们通过实验在图像和音频数据集上进行了IDEcode的功效，从而获得了最新的结果。我们还表明，IDEcode可以检测对抗性示例。
Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence on inputs outside their training distribution. The deployment of DNNs in safety-critical domains requires detection of out-of-distribution (OOD) data so that DNNs can abstain from making predictions on those. A number of methods have been recently developed for OOD detection, but there is still room for improvement. We propose the new method iDECODe, leveraging in-distribution equivariance for conformal OOD detection. It relies on a novel base non-conformity measure and a new aggregation method, used in the inductive conformal anomaly detection framework, thereby guaranteeing a bounded false detection rate. We demonstrate the efficacy of iDECODe by experiments on image and audio datasets, obtaining state-of-the-art results. We also show that iDECODe can detect adversarial examples.
