Abstract
Unsupervised anomaly detection methods based on the Generative Adversarial Network have solved the problem of supervised anomaly detection methods relying on the training of known anomaly samples. However, the encoder is so powerful as to reconstruct the abnormal samples well, eventually resulting in missed detection. To address this problem, this paper proposes a memory enhancement method based on Skip-GANomaly for anomaly detection to optimize the generator. During the training process, the number of skip-connection layers is adjusted to reduce the generator overfitting. The coded information is used as query in the memory enhancement module attention to retrieve the most relevant items in the module memory and the memory content can be updated and frozen, so as to improve the reliability of the coding information, increase the error of anomaly reconstruction, finally to improve the detection accuracy. The average AUC values of this method tested on the public datasets MNIST and CIFAR-10 reach 0.905 and 0.851, improved by 15.0% and 12.0%, respectively. It fully indicates the versatility and effectiveness of the method described in this paper.
Similar content being viewed by others
Data Availability
The data generated in the course of the current study may be obtained from the corresponding author on reasonable request.
References
Akcay S, Atapour-Abarghouei A, Breckon T P (2019) Skip-ganomaly: Skip connected and adversarially trained encoder-decoder anomaly detection. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp 1–8
Akcay S, Atapour-Abarghouei A, Breckon TP (2018) Ganomaly: Semi-supervised anomaly detection via adversarial training. In: Asian conference on computer vision, pp 622–637
Chalapathy R, Chawla S (2019) Deep Learning for Anomaly Detection: A Survey. arXiv:1901.03407
Cheng Z, Wang S, Zhang P et al (2021) Improved autoencoder for unsupervised anomaly detection. Int J Intell Systs 36(12):7103–7125
Deng L (2012) The mnist database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Proc Mag 29(6):141–142
Erfani SM, Baktashmotlagh M, Moshtaghi M et al (2017) From Shared Subspaces to Shared Landmarks: A Robust Multi-Source Classification Approach. In: Thirty-First AAAI Conference on Artificial Intelligence
Fei Y, Huang C, Jinkun C et al (2020) Attribute restoration framework for anomaly detection. In: IEEE Transactions on Multimedia
Gong D, Liu L, Le V et al (2020) Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection. In: 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pp 1705–1714
Goodfellow I, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. In: Advances in neural information processing systems
Graves A, Wayne G, Danihelka I (2014) Computer Science. Neural turing machines. arXiv:1410.5401
Hou J, Zhang Y, Zhong Q et al (2021) Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 8791–8800
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, pp 448–456
Javaid A, Niyaz Q, Sun W et al (2016) A deep learning approach for network intrusion detection system. Eai Endorsed Trans Secur Saf 3(9):e2
Jumutc V, Suykens JA (2014) Multi-class supervised novelty detection. IEEE Trans Pattern Anal Mach Intell 36(12):2510–2523
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980
Kingma DP, Welling M (2014) Auto-encoding variational bayes. arXiv preprint. In: 2nd International Conference on Learning Representations (ICLR) 14
Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images 7
Lai CH, Zou D, Lerman G (2019) Robust subspace recovery layer for unsupervised anomaly detection. arXiv:1904.00152
Ling CX, Huang J, Zhang H (2003) AUC: a statistically consistent and more discriminating measure than accuracy. In: Ijcai, pp 519–524
Liu G, Lan S, Zhang T et al (2021) SAGAN: Skip-Attention GAN For Anomaly Detection. In: 2021 IEEE International Conference on Image Processing (ICIP), pp 2468–2472
Liu W, Luo W, Lian D et al (2018) Future frame prediction for anomaly detection–a new baseline. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6536–6545
Luo W, Liu W, Gao S (2017) A revisit of sparse coding based anomaly detection in stacked rnn framework. In: Proceedings of the IEEE International Conference on Computer Vision, pp 341–349
Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models, In: Proc. icml 3
Meng Q, Catchpoole D, Skillicom D et al (2017) Relational autoencoder for feature extraction. In: 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 364–371
Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Icml, pp 807–814
Nguyen TN, Meunier J (2019) Anomaly detection in video sequence with appearance-motion correspondence. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 1273–1283
Null N (2014) Toward supervised anomaly detection. J Artif Intell Res 235–262
Park H, Noh J, Ham B (2020) Learning memory-guided normality for anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 14372–14381
Paszke A, Gross S, Chintala S et al (2017) Automatic differentiation in pytorch
Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434
Ronneberger O , Fischer P, Brox T (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp 234–241
Ruff L, Vandermeulen R, Goernitz N et al (2018) Deep one-class classification. In:International conference on machine learning, pp 4393–4402
Schlegl T, Seeböck P, Waldstein SM et al (2017) Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: International conference on information processing in medical imaging. Springer, Cham, pp 146-157
Shilton A, Rajasegarar S, Palaniswami M (2013) Combined multiclass classification and anomaly detection for large-scale wireless sensor networks. In: 2013 IEEE eighth international conference on intelligent sensors, sensor networks and information processing, pp 491–496
Škvára V, Pevný T, Šmídl V (2018) Are generative deep models for novelty detection truly better?. arXiv:1807.05027
Xu H, Chen W, Zhao N et al (2018) Unsupervised anomaly detection via variational auto-encoder for seasonal kpis in web applications.In: Proceedings of the 2018 World Wide Web Conference, pp 187–196
Zenati H, Foo CS, Lecouat B, Manek G, Chandrasekhar VR (2018) Efficient gan-based anomaly detection. arXiv:1802.06222
Zhao B, FF Li, Xing EP (2011) Online detection of unusual events in videos via dynamic sparse coding. In: 2011 Computer Vision & Pattern Recognition(CVPR). IEEE, pp 3313–3320
Funding
National Natural Science Foundation of China(61960206010).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare no conflicts of interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jiang, W., Yang, K., Qiu, C. et al. Memory enhancement method based on Skip-GANomaly for anomaly detection. Multimed Tools Appl 83, 19501–19516 (2024). https://doi.org/10.1007/s11042-023-16317-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16317-6