Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data. Previous progress has introduced various approaches where the in-distribution training data and even several OOD examples are prerequisites. However, due to privacy and security, auxiliary data tends to be impractical in a real-world scenario. In this paper, we propose a data-free method without training on natural data, called Class-Conditional Impressions Reappearing (C2IR), which utilizes image impressions from the fixed model to recover class-conditional feature statistics. Based on that, we introduce Integral Probability Metrics to estimate layer-wise class-conditional deviations and obtain layer weights by Measuring Gradient-based Importance (MGI). The experiments verify the effectiveness of our method and indicate that C2IR outperforms other post-hoc methods and reaches comparable performance to the full access (ID and OOD) detection method, especially in the far-OOD dataset (SVHN).

翻译：分布外（OOD）检测旨在增强标准深度神经网络，使其能够将异常输入与原始训练数据区分开来。以往的研究提出了多种方法，这些方法通常以分布内训练数据甚至若干分布外样本为前提条件。然而，由于隐私和安全因素，辅助数据在实际应用场景中往往难以实现。本文提出一种无需自然数据训练的无数据方法——类条件印象重现（C2IR），该方法利用固定模型生成的图像印象来恢复类条件特征统计量。在此基础上，我们引入积分概率度量以估计逐层类条件偏差，并通过基于梯度的重要性度量（MGI）获取各层权重。实验验证了该方法的有效性，结果表明C2IR优于其他事后处理方法，并在远分布数据集（SVHN）上达到了与全访问（分布内和分布外）检测方法相当的性能。