论文标题
使用高度污染的数据，具有深层生成模型的粒状学习
Granular Learning with Deep Generative Models using Highly Contaminated Data
论文作者
论文摘要
一种方法，利用最新的归一化流模型详细介绍了具有质量问题的真实世界图像数据集中的颗粒（连续）意义上的异常检测的最新进展，并在许多其他应用程序/域/数据类型中含义。该方法是完全无监督的（没有可用的注释），但定性地显示了通过缩放的对数可能性覆盖的图像的热图为图像提供准确的语义标记。根据每个图像的中位值进行分类时，会观察到质量清晰的趋势。此外，通过使用标准化流量模型的对数可能性输出作为特征提取卷积神经网络的训练信号，下游分类通过弱监督的方法证明是可能且有效的。 CNN上的线性密集层输出显示可拆除高级表示形式，并有效地聚集了各种质量问题。因此，可以证明一种完全无通道（完全无监督的）方法，以进行准确的质量问题估算和分类。
An approach to utilize recent advances in deep generative models for anomaly detection in a granular (continuous) sense on a real-world image dataset with quality issues is detailed using recent normalizing flow models, with implications in many other applications/domains/data types. The approach is completely unsupervised (no annotations available) but qualitatively shown to provide accurate semantic labeling for images via heatmaps of the scaled log-likelihood overlaid on the images. When sorted based on the median values per image, clear trends in quality are observed. Furthermore, downstream classification is shown to be possible and effective via a weakly supervised approach using the log-likelihood output from a normalizing flow model as a training signal for a feature-extracting convolutional neural network. The pre-linear dense layer outputs on the CNN are shown to disentangle high level representations and efficiently cluster various quality issues. Thus, an entirely non-annotated (fully unsupervised) approach is shown possible for accurate estimation and classification of quality issues..
