论文标题
使用标准化流量和对比数据的图像离群值检测的正差分分布
Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data
论文作者
论文摘要
检测与培训数据偏离的测试数据是安全且健壮的机器学习的核心问题。通过生成模型学到的可能性，例如，通过标准对数似然训练的归一流流程，作为离群得分的表现不佳。我们建议使用一个未标记的辅助数据集和一个概率离群值分数进行离群检测。我们使用在辅助数据集上训练的自我监管的特征提取器，并通过最大程度地提高分布数据的可能性并最大程度地减少对比数据集的可能性，并在提取功能上训练归一化流量。我们表明，这等同于学习分布和对比特征密度之间的归一化正差。我们在基准数据集上进行实验，并与可能性，可能性比和最新异常检测方法进行比较。
Detecting test data deviating from training data is a central problem for safe and robust machine learning. Likelihoods learned by a generative model, e.g., a normalizing flow via standard log-likelihood training, perform poorly as an outlier score. We propose to use an unlabelled auxiliary dataset and a probabilistic outlier score for outlier detection. We use a self-supervised feature extractor trained on the auxiliary dataset and train a normalizing flow on the extracted features by maximizing the likelihood on in-distribution data and minimizing the likelihood on the contrastive dataset. We show that this is equivalent to learning the normalized positive difference between the in-distribution and the contrastive feature density. We conduct experiments on benchmark datasets and compare to the likelihood, the likelihood ratio and state-of-the-art anomaly detection methods.
