Autoencoders Without Reconstruction for Textural Anomaly Detection
Autoencoders Without Reconstruction for Textural Anomaly Detection
复制标题
DOI：
10.1109/ijcnn52387.2021.9533804
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Philip A. Adey;S. Akçay;M. Bordewich;T. Breckon
中科院分区：
文献类型：
--
作者：
Philip A. Adey;S. Akçay;M. Bordewich;T. Breckon
自然纹理中的自动异常检测是一系列高速、高产量制造行业质量控制中的关键组件，这些行业依赖基于相机的视觉检测技术。通过使用自动编码器重建误差来瞄准异常检测容易地促进对通常更丰富的非异常样本集合的训练，而不需要可能难以来源的代表性异常训练样本集合。不幸的是，自动编码器很难重建高频视觉信息，因此，这种方法通常不能为非异常像素实现足够低的重建误差。在本文中，我们提出了一种新的方法，其中自动编码器被训练来直接输出期望的每像素异常测量，而不需要首先执行重建。这是通过用噪声破坏训练样本，然后预测像素需要如何移位以去除噪声来实现的。我们的直接方法使模型能够将正常像素的异常分数压缩到接近于零的严格范围内，从而产生非常干净的异常分段，从而显著提高性能。我们还引入了反射REU输出激活函数，通过保持落在图像动态范围内的值不变，该函数更好地促进了在这种直接机制下的训练。总体而言，在MVTecAD基准数据集的纹理类别上，ROC曲线下的平均面积达到96%，超过了目前所有最先进的方法所实现的面积。
Automatic anomaly detection in natural textures is a key component within quality control for a range of high-speed, high-yield manufacturing industries that rely on camera-based visual inspection techniques. Targeting anomaly detection through the use of autoencoder reconstruction error readily facilitates training on an often more plentiful set of non-anomalous samples, without the explicit need for a representative set of anomalous training samples that may be difficult to source. Unfortunately, autoencoders struggle to reconstruct high-frequency visual information and therefore, such approaches often fail to achieve a low enough reconstruction error for non-anomalous pixels. In this paper, we propose a new approach in which the autoencoder is trained to directly output the desired per-pixel measure of abnormality without first having to perform reconstruction. This is achieved by corrupting training samples with noise and then predicting how pixels need to be shifted so as to remove the noise. Our direct approach enables the model to compress anomaly scores for normal pixels into a tight bound close to zero, resulting in very clean anomaly segmentations that significantly improve performance. We also introduce the Reflected ReLU output activation function that better facilitates training under this direct regime by leaving values that fall within the image dynamic range unmodified. Overall, an average area under the ROC curve of 96% is achieved on the texture classes of the MVTecAD benchmark dataset, surpassing that achieved by all current state-of-the-art methods.