we exploit multiple transformations in training and evaluation. In contrast to most other methods, ours does not require a large number of training samples and performs well with as low as 16 images
In industrial manufacturing processes the quality of the products is constantly monitored and improved.
if some defect types are known, new types can still occur any time due to unforeseeable events during manufacturing.
We propose a solution for semi-supervised defect detection where only positive examples and no defective examples are present during training. This is also known as anomaly detection.
Defect detection is a specific sub-problem where visually similar normal samples and only slightly different anomalous samples are present. While traditional anomaly detection methods are well-suited to data with high intra-class variance, they are not able to capture subtle differences.
전통적인 기법들은 이러한 미묘한 차이를 구분못함 항상 high intra class variance밖에 못함
We tackle this problem by employing an accurate density esti-mator
connvolution neural network에 의해서..
normal sample의 feature distribution은 NF의 latent space를 활용함
Unlike other generative models such as variational autoencoders [17] or GANs [12], there exists a bijective mapping between feature space and latent space in which each vector is assigned to a likelihood.(일대일 대응) feature space<>latent space
픽쳐스페이스에 있는 픽쳐벡터들이 가능도에 할당됨
디퍼넷이 각각의 이미지의 가능도를 계산하도록 도움