Abstract
In industrial vision, the anomaly detection problem can be addressed with an autoencoder trained to map an arbitrary image, i.e. with or without any defect, to a clean image, i.e. without any defect. In this approach, anomaly detection relies conventionally on the reconstruction residual or, alternatively, on the reconstruction uncertainty. To improve the sharpness of the reconstruction, we consider an autoencoder architecture with skip connections. In the common scenario where only clean images are available for training, we propose to corrupt them with a synthetic noise model to prevent the convergence of the network towards the identity mapping, and introduce an original Stain noise model for that purpose. We show that this model favors the reconstruction of clean images from arbitrary real-world images, regardless of the actual defects appearance. In addition to demonstrating the relevance of our approach, our validation provides the first consistent assessment of reconstruction-based methods, by comparing their performance over the MVTec AD dataset [1], both for pixel- and image-wise anomaly detection. Our implementation is available at https://github.com/anncollin/AnomalyDetection-Keras.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bergmann P, Fauser M, Sattlegger D, Steger C (2019) MVTec AD - a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 9592–9600
Pimentel MAF, Clifton DA, Clifton L, Tarassenko L (2014) A review of novelty detection. Signal Process 99:215–249
Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey. ACM Comput Surv (CSUR) 41:1–58
Rahmatov N, Paul A, Saeed F, Hong WH, Seo HC, Kim J (2019) Machine learning-based automated image processing for quality management in industrial Internet of Things. Int J Distrib Sens Netw (IJDSN), 15(10)
Seebock P (2019) Exploiting epistemic uncertainty of anatomy segmentation for anomaly detection in retinal OCT. IEEE Trans Med Imaging 39(1):87–98
Huang C, Cao J, Ye F, Li M, Zhang Y, Lu C (2019) Inverse-transform autoencoder for anomaly detection. arXiv preprint arXiv:1911.10676
Kendall A, Gal Y (2017) What uncertainties do we need in Bayesian deep learning for computer vision? In: Proceedings of the advances in neural information processing systems conference (NeurIPS), pp 5574–5584
Collin A-S, de Vleeschouwer C (2021) Improved anomaly detection by training an autoencoder with skip connections on images corrupted with stain-shaped noise. In: Proceedings of the international conference on pattern recognition (ICPR)
Carrera D, Boracchi G, Foi A, Wohlberg B (2015) Detecting anomalous structures by convolutional sparse models. In: Proceedings of the international joint conference on neural networks (IJCNN), pp 1–8
Napoletano P, Piccoli F, Schettini R (2018) Anomaly detection in nanofibrous materials by CNN-based self-similarity. Sensors 18(1):209
Staar B, Lütjen M, Freitag M (2019) Anomaly detection with convolutional neural networks for industrial surface inspection. Procedia CIRP 79:484–489
Zhou C, Paffenroth RC (2017) Anomaly detection with robust deep autoencoders. In: Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD), pp 665–674
Leveni F, Deib M, Boracchi G, Alippi C (2021) PIF: anomaly detection via preference embedding. In: Proceedings of the international conference on pattern recognition (ICPR)
Zhao H, Gallo O, Frosio I, Kautz J (2016) Loss functions for image restoration with neural networks. IEEE Trans Comput Imaging 3(1):47–57
Bergmann P, Löwe S, Fauser M, Sattlegger D, Steger C (2019) Improving unsupervised defect segmentation by applying structural similarity to autoencoders. In: Proceedings of the international joint conference on computer vision, imaging and computer graphics theory and applications (VISIGRAPP), pp 372–380
Sabokrou M, Khalooei M, Fathy M, Adeli E (2018) Adversarially learned one-class classifier for novelty detection. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition (CVPR), pp 3379–3388
Schlegl T, Seeböck P, Waldstein SM, Schmidt-Erfurth U, Langs G (2017) Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: Proceedings of the international conference on information processing in medical imaging (IPMI), pp 146–157
Schlegl T, Seeböck P, Waldstein SM, Langs G, Schmidt-Erfurth U (2019) f-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks. Med Image Anal 54:30–44
Akçay S, Atapour-Abarghouei A, Breckon TP (2019) Skip-GANomaly: skip connected and adversarially trained encoder-decoder anomaly detection. In: Proceedings of the international joint conference on neural networks (IJCNN), pp 1–8
Baur C, Wiestler B, Albarqouni S, Navab N (2018) Deep autoencoding models for unsupervised anomaly segmentation in brain MR images. In: Proceedings of the international MICCAI Brainlesion workshop, pp 161–169
Radford A, Metz L, Chintala S (2016) Unsupervised representation learning with deep convolutional generative adversarial networks. In: Proceedings of the international conference on learning representations (ICLR), pp 1–16
Goodfellow I, et al (2014) Generative adversarial nets. In: Proceedings of the advances in neural information processing systems conference (NeurIPS), pp 2672–2680
Snell J, et al (2017) Learning to generate images with perceptual similarity metrics. In: Proceedings of the IEEE international conference on image processing (ICIP), pp 4277–4281
Dehaene D, Frigo O, Combrexelle S, Eline P (2020) Iterative energy-based projection on a normal data manifold for anomaly localization. In: Proceedings of the international conference on learning representations (ICLR)
Haselmann M, Gruber DP, Tabatabai P (2018) Anomaly detection using deep learning based image completion. In: Proceedings of the IEEE international conference on machine learning and applications (ICMLA), pp 1237–1242
Munawar A, Creusot C (2015) Structural inpainting of road patches for anomaly detection. In: Proceedings of the IAPR international conference on machine vision applications (MVA), pp 41–44
Zavrtanik V, Kristan M, Skočaj D (2021) Reconstruction by inpainting for visual anomaly detection. Pattern Recogn 112:107706
Mei S, Wang Y, Wen G (2018) Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model. Sensors 18(4):1064
Gong D, et al (2019) Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF international conference on computer vision (ICCV), pp 1705–1714
Wang L, Zhang D, Guo J, Han Y (2020) Image anomaly detection using normal data only by latent space resampling. Appl Sci 10(23):8660–8679
Van den Oord A, Vinyals O, Kavukcuoglu K (2017) Neural discrete representation learning. Proc Adv Neural Inf Process Syst Conf (NeurIPS) 30:6306–6315
Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In Proceedings of the international conference on medical image computing and computer-assisted intervention (MICCAI), pp 234–241
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: Proceedings of the international conference on learning representations (ICLR)
Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. In: Proceedings of the AAAI conference on artificial intelligence, pp 13001–13008
Fong R, Vedaldi A (2019) Occlusions for effective data augmentation in image classification. In: Proceedings of the international conference on computer vision workshop (ICCVW), pp 4158–4166
Liu G, Reda FA, Shih KJ, Wang TC, Tao A, Catanzaro B (2018) Image inpainting for irregular holes using partial convolutions. In: Proceedings of the European conference on computer vision (ECCV), pp 85–100
Rippel O, Mertens P, Merhof D (2020) Modeling the distribution of normal data in pre-trained deep features for anomaly detection. arXiv preprint arXiv:2005.14140
Massoli FV, Falchi F, Kantarci A, Akti Ş, Ekenel HK, Amato G (2020) MOCCA: multi-layer one-class classification for anomaly detection. arXiv preprint arXiv:2012.12111
Lee K, Lee K, Lee H, Shin J (2018) A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In: Proceedings of the advances in neural information processing systems conference (NeurIPS), pp 7167–7177
Granda R, Tuytelaars T, Oramas J (2020) Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks? arXiv preprint arXiv:2010.15974
Abati D, Porrello A, Calderara S, Cucchiara R (2019) Latent space autoregression for novelty detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 481–490
Acknowledgments
Part of this work has been funded by the “Pôle Mecatech ADRIC” Walloon Region project, and by the Belgian National Fund for Scientific Research (FRS-FNRS).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Collin, AS., De Vleeschouwer, C. (2022). Joint Use of Skip Connections and Synthetic Corruption for Anomaly Detection with Autoencoders. In: Tran, K.P. (eds) Control Charts and Machine Learning for Anomaly Detection in Manufacturing. Springer Series in Reliability Engineering. Springer, Cham. https://doi.org/10.1007/978-3-030-83819-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-83819-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-83818-8
Online ISBN: 978-3-030-83819-5
eBook Packages: EngineeringEngineering (R0)