摘要
基于自编码器(AE)的异常检测方法利用重构误差判断待测样本是正常数据还是异常数据。然而,上述方法在正常数据与异常数据上产生的重构误差非常接近,导致部分异常数据很容易被错分为正常数据。为解决上述问题,提出一种由两个并行的AE和一个Transformer网络组成的异常检测方法——DATN-ND。首先,Transformer网络利用输入样本的瓶颈特征生成伪异常数据的瓶颈特征,从而在训练集中增加异常数据信息;其次,双AE将带有异常数据信息的瓶颈特征尽可能地重构为正常数据,增加异常数据与正常数据的重构误差差别。与记忆增强自编码器(MemAE)相比,DATN-ND在MNIST、Fashion-MNIST、CIFAR-10数据集上ROC曲线下面积(AUC)分别提升6.8、12.0和2.5个百分点。实验结果表明,DATN-ND能够有效扩大正常数据和异常数据在重构误差上的差别。
AutoEncoder(AE) based novelty detection method utilizes reconstruction error to classify the test samples to be normal or novel data. However, the above method produces very close reconstruction errors on normal data and novel data. Therefore, some novel data are easy to be misclassified as normal data. To solve the above problem, a novelty detection method composed of two parallel AEs and one Transformer network was proposed, namely Novelty Detection based on Dual Autoencoders and Transformer Network(DATN-ND). Firstly, the bottleneck features of input samples were used by Transformer network to generate the bottleneck features with pseudo-novel data, thereby increasing the novel data information in the training set. Secondly, the bottleneck features with novel data information were reconstructed by the dual AEs to normal data as much as possible, increasing the reconstruction error difference between novel and normal data.Compared with MemAE(Memory-augmented AE), DATN-ND has the Area Under the Receiver Operating Characteristic curve(AUC) improved by 6. 8 percentage points, 12. 0 percentage points, and 2. 5 percentage points respectively on MNIST, Fashion-MNIST, and CIFAR-10 datasets. Experimental results show that DATN-ND can effectively make the difference of reconstruction error between normal data and abnormal data bigger.
作者
周佳航
邢红杰
ZHOU Jiahang;XING Hongjie(College of Mathematics and Information Science,Hebei University,Baoding Hebei 071002,China;Hebei Key Laboratory of Machine Learning and Computational Intelligence(Hebei University),Baoding Hebei 071002,China)
出处
《计算机应用》
CSCD
北大核心
2023年第1期22-29,共8页
journal of Computer Applications
基金
国家自然科学基金资助项目(61672205)
河北省自然科学基金资助项目(F2017201020)。
