Anomaly Machine Component Detection by Deep Generative Model with Unregularized Score
Anomaly Machine Component Detection by Deep Generative Model with Unregularized Score
复制标题
DOI：
10.1109/ijcnn.2018.8489169
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Takashi Matsubara;Ryosuke Tachibana;K. Uehara
中科院分区：
文献类型：
--
作者：
Takashi Matsubara;Ryosuke Tachibana;K. Uehara
制造厂最常见的需求之一是将不符合标准的产品作为异常拒收。准确、自动的异常检测提高了产品的可靠性，降低了检测成本。概率模型已经被用来以非监督的方式将概率较低的测试样本检测为异常。最近，一种称为深度生成模型(DGM)的概率模型被提出用于自然图像的端到端建模，并已取得了一定的成功。然而，复杂结构机械部件的异常检测仍然具有挑战性，因为它们产生了种类繁多的低概率正常图像块。为了克服这一困难，我们提出了DGM的非正则化评分。顾名思义，非正则化分数就是不含正则项的DGM的异常分数。非正则化分数对样本的内在复杂性具有健壮性，并且具有较小的拒绝样本的风险，该样本出现的频率较低，但与标准相符。
One of the most common needs in manufacturing plants is rejecting products not coincident with the standards as anomalies. Accurate and automatic anomaly detection improves product reliability and reduces inspection cost. Probabilistic models have been employed to detect test samples with lower likelihoods as anomalies in unsupervised manner. Recently, a probabilistic model called deep generative model (DGM) has been proposed for end-to-end modeling of natural images and already achieved a certain success. However, anomaly detection of machine components with complicated structures is still challenging because they produce a wide variety of normal image patches with low likelihoods. For overcoming this difficulty, we propose unregularized score for the DGM. As its name implies, the unregularized score is the anomaly score of the DGM without the regularization terms. The unregularized score is robust to the inherent complexity of a sample and has a smaller risk of rejecting a sample appearing less frequently but being coincident with the standards.