结合多解码器与两阶段通道选择的异常检测方法

doi:10.19678/j.issn.1000-3428.0064373

摘要/Abstract

摘要： 异常检测是发现数据集中不符合明确定义的模式（或样本）的过程。目前流行的异常检测方法通常只对合群点进行建模，忽视了潜藏在无标记数据中的丰富信息，导致出现过拟合、阈值依赖等问题。此外，部分现有方法同等地处理正常类和异常类，与异常检测的目的相矛盾。提出一种结合多解码器与两阶段通道选择的异常检测方法，采用一种全新的重构-选择模型代替重构-排序-拒绝模型，并分别对合群点和离群点进行解码建模，构造一个无须阈值的选择器以区分两者，降低阈值确定过程中产生的人为误差和计算开销。通道选择器以两阶段的方式为样本分配通道，在第一阶段使用注意力选择器为无标记样本选择最佳匹配的离群点通道，在第二阶段使用竞争式选择器在合群点通道和最佳离群点通道中选择更适合的一个作为目标通道。两阶段选择器的结构能避免出现局部极值点，并可以利用直接引入的监督信息对选择结果进行修正。实验结果表明，与U-Std、ARAE、AnoGAN等流行方法相比，该方法的检测性能更好，在MNIST、Fashion-MNIST、CIFAR-10数据集上的AUROC值分别为99.3%、96.9%和90.5%。

关键词: 异常检测, 非对称建模, 数据增强, 数据集清理, 免阈值

Abstract: Anomaly detection is the process of finding patterns(or samples) in data that do not conform to well-defined behavior. Current popular anomaly detection methods always merely model the inliers, whilst ignoring the rich information that is contained in unlabeled data, leading to problems such as overfitting and threshold dependence. Meanwhile several methods treat normal and abnormal classes equally, which contradicts with the purpose of anomaly detection. A method for anomaly detection combining multi-decoder and two-stage channel selection is proposed. This technique adopts a brand new reconstruct-and-select framework to replace reconstruct-rank-reject framework, models Inliers and Outliers by decoding respectively, whilst building a threshold-free selector to distinguish amongst them, diminishing the human error and computational cost of threshold determination. The channel selector works in a two-stage fashion:at the first tage, the attentive selector chooses the best matching outlier channel for unlabeled sample;at the second stage, the competing selector decides whether the better target channel is Inlier channel or Outlier channel. The two-stage structure of selector makes it avoid local extremum and utilize directly introduced supervision information to correct the selection result. Experimental results demonstrate the detection performance of this method is better than U-Std, ARAE, AnoGAN and other popular methods, with the Area Under the Receiver Operating Characteristic Curve (AUROC) value on classes of MNIST, Fashion-MNIST and CIFAR-10 datasets reaching 99.3%, 96.9% and 90.5% respectively.

Key words: anomaly detection, asymmetric modeling, data augmentation, dataset cleaning, threshold-free

中图分类号:

TP181

王禹博, 陈利锋, 许卫霞. 结合多解码器与两阶段通道选择的异常检测方法[J]. 计算机工程, 2023, 49(3): 37-48.

WANG Yubo, CHEN Lifeng, XU Weixia. Anomaly Detection Method Combining with Multi-Decoder and Two-Stage Channel Selection[J]. Computer Engineering, 2023, 49(3): 37-48.

https://www.ecice06.com/CN/Y2023/V49/I3/37

图/表 13

20230314184418

20230314184421

20230314184424

20230314184427

20230314184430

20230314184434

20230314184437

20230314184440

20230314184443

20230314184448

20230314184451

20230314184454

20230314184457

参考文献

[1] KHAN S S, MADDEN M G.One-Class classification:taxonomy of study and review of techniques[J].The Knowledge Engineering Review, 2014, 29(3):345-374.
[2] ROUSSEEUW P J, DRIESSEN K V.A fast algorithm for the minimum covariance determinant estimator[J].Technometrics, 1999, 41(3):212-223.
[3] CHEN Y Q, ZHOU X S, HUANG T S.One-Class SVM for learning in image retrieval[C]//Proceedings of International Conference on Image.Washington D.C., USA:IEEE Press, 2001:34-37.
[4] LIU F T, TING K M, ZHOU Z H.Isolation-based anomaly detection[EB/OL].[2022-03-03].https://dl.acm.org/doi/10.1145/2133360.2133363.
[5] BREUNIG M M, KRIEGEL H P, NG R T, et al.Lof:identifying density-based local outliers[C]//Proceedings of the 3rd European Conference on Principles of Data Mining and Knowledge Discovery.Berlin, Germany:Springer, 1999:262-270.
[6] CANDÈS E J, LI X, MA Y, et al.Robust principal component analysis?[EB/OL].[2022-03-03].https://www.zhangqiaokeyan.com/open-access_resources_thesis/0100057689306.html.
[7] LI P, HASTIE T J, CHURCH K W.Very sparse random projections[C]//Proceedings of the 12th International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2006:287-296.
[8] BENGIO Y, COURVILLE A, VINCENT P.Representation learning:a review and new perspectives[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8):1798-1828.
[9] IONESCU R T, SMEUREANU S, ALEXE B, et al.Unmasking the abnormal events in video[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2017:2914-2922.
[10] ANDREWS J, TANAY T, MORTON E J, et al.Transfer representation-learning for anomaly detection[EB/OL].[2022-03-03].https://www.researchgate.net/publication/317424976_Transfer_Representation-Learning_for_Anomaly_Detection.
[11] HAWKINS S, HE H, WILLIAMS G J, et al.Outlier detection using replicator neural networks[EB/OL].[2022-03-03].https://link.springer.com/chapter/10.1007/3-540-46145-0_17.
[12] SCHLEGL T, SEEBÖCK P, WALDSTEIN S M, et al.Unsupervised anomaly detection with generative adversarial networks to guide marker discovery[C]//Processing of the 25th International Conference on Medical Imaging.Berlin, Germany:Springer, 2017:146-157.
[13] SABOKROU M, KHALOOEI M, FATHY M, et al.Adversarially learned one-class classifier for novelty detection[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.New York, USA:ACM Press, 2018:3379-3388.
[14] PANG G S, YAN C, SHEN C H, et al.Self-trained deep ordinal regression for end-to-end video anomaly detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:12170-12179.
[15] CHEN T, TANG L, SUN Y, et al.Entity embedding-based anomaly detection for heterogeneous categorical events[EB/OL].[2022-03-03].https://arxiv.org/abs/1608.07502.
[16] GUTMANN M, HYVÄRINEN A.Noise-contrastive estimation:a new estimation principle for unnormalized statistical models[EB/OL].[2022-03-03].http://proceedings.mlr.press/v9/gutmann10a.html.
[17] ZHAI S, CHENG Y, LU W, et al.Deep structured energy based models for anomaly detection[C]//Proceedings of the 33rd International Conference on Machine Learning.New York, USA:ACM Press, 2016:1100-1109.
[18] VINCENT P, LAROCHELLE H, LAJOIE I, et al.Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J].Journal of Machine Learning Research 2010, 11:3371-3408.
[19] BAHDANAU D, CHO K, BENGIO Y.Neural machine translation by jointly learning to align and translate[EB/OL].[2022-03-03].https://arxiv.org/abs/1409.0473.
[20] LECUN Y, BOTTOU L, BENGIO Y, et al.Gradient-based learning applied to document recognition[EB/OL].[2022-03-03].https://www.mendeley.com/catalogue/d2be456a-aed9-3e9a-9ea4-388e020a82d9/.
[21] HULL J J.A database for handwritten text recognition research[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(5):550-554.
[22] XIAO H, RASUL K, VOLLGRAF R.Fashion-MNIST:a novel image dataset for benchmarking machine learning algorithms[EB/OL].[2022-03-03].https://arxiv.org/abs/1708.07747.
[23] KRIZHEVSKY A, HINTON G.Learning multiple layers of features from tiny image[EB/OL].[2022-03-03].https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf.
[24] SALEHI M, ARYA A, PAJOUM B, et al.ARAE:adversarially robust training of autoencoders improves novelty detection[J].Neural Networks, 2021, 144:726-736.
[25] RUFF L, GÖRNITZ N, DEECKE L, et al.Deep one-class classification[EB/OL].[2022-03-03].http://proceedings.mlr.press/v80/ruff18a.html.
[26] GOLAN I, EL-YANIV R.Deep anomaly detection using geometric transformations[EB/OL].[2022-03-03].https://arxiv.org/abs/1805.10917.
[27] LI X, KIRINGA I, YEAP T H, et al.Exploring deep anomaly detection methods based on capsule net[C]//Proccedings of the 33rd Canadian Conference on Artificial Intelligence.Berlin, Germany:Springer, 2020:375-387.
[28] PERERA P, NALLAPATI R, XIANG B.OCGAN:one-class novelty detection using GANs with constrained latent representations[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:2893-2901.
[29] ABATI D, PORRELLO A, CALDERARA S, et al.Latent space autoregression for novelty detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:481-490.
[30] VENKATARAMANAN S, PENG K C, SINGH R V, et al.Attention guided anomaly localization in images[EB/OL].[2022-03-03].https://link.springer.com/chapter/10.1007/978-3-030-58520-4_29.
[31] BERGMANN P, FAUSER M, SATTLEGGER D, et al.Uninformed students:student-teacher anomaly detection with discriminative latent embeddings[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2020:4182-4191.
[32] SALEHI M, SADJADI N, BASELIZADEH S, et al.Multiresolution knowledge distillation for anomaly detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2021:14897-14907.
[33] ZONG B, SONG Q, MIN M R, et al.Deep autoencoding Gaussian mixture model for unsupervised anomaly detection[EB/OL].[2022-03-03].https://openreview.net/forum?id=BJJLHbb0.
[34] GOYAL S, RAGHUNATHAN A, JAIN M, et al.DROCC:deep robust one-class classification[EB/OL].[2022-03-03].http://proceedings.mlr.press/v119/goyal20c.html.
[35] SALEHI M, EFTEKHAR A, SADJADI N, et al.Puzzle-AE:novelty detection in images through solving puzzles[EB/OL].[2022-03-03].https://arxiv.org/abs/2008.12959.
[36] CHAN W, JAITLY N, LE Q, et al.Listen, attend and spell:a neural network for large vocabulary conversational speech recognition[C]//Proceedings of 2016 IEEE International Conference on Acoustics, Speech and Signal.Washington D.C., USA:IEEE Press, 2016:4960-4964.

选择文件类型/文献管理软件名称

选择包含的内容