GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module

Anomaly detection is nowadays increasingly used in industrial applications and processes. One of the main fields of the appliance is the visual inspection for surface anomaly detection, which aims to spot regions that deviate from regularity and consequently identify abnormal products. Defect localization is a key task that is usually achieved using a basic comparison between generated image and the original one, implementing some blob analysis or image-editing algorithms in the postprocessing step, which is very biased towards the source dataset, and they are unable to generalize. Furthermore, in industrial applications, the totality of the image is not always interesting but could be one or some regions of interest (ROIs), where only in those areas there are relevant anomalies to be spotted. For these reasons, we propose a new architecture composed by two blocks. The first block is a generative adversarial network (GAN), based on a residual autoencoder (ResAE), to perform reconstruction and denoising processes, while the second block produces image segmentation, spotting defects. This method learns from a dataset composed of good products and generated synthetic defects. The discriminative network is trained using a ROI for each image contained in the training dataset. The network will learn in which area anomalies are relevant. This approach guarantees the reduction of using preprocessing algorithms, formerly developed with blob analysis and image-editing procedures. To test our model, we used challenging MVTec anomaly detection datasets and an industrial large dataset of pharmaceutical BFS strips of vials. This set constitutes a more realistic use case of the aforementioned network.

[1]  Kilian Batzner,et al.  EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies , 2023, ArXiv.

[2]  Seyun Kim,et al.  PNI : Industrial Anomaly Detection using Position and Neighborhood Information , 2022, 2211.12634.

[3]  Yuhui Huang,et al.  RDAD: A reconstructive and discriminative anomaly detection model based on transformer , 2022, Int. J. Intell. Syst..

[4]  C. Steger,et al.  Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization , 2022, International Journal of Computer Vision.

[5]  Xuan Xia,et al.  GAN-based anomaly detection: A review , 2022, Neurocomputing.

[6]  D. Skočaj,et al.  DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Kazuki Kozuka,et al.  CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows , 2021, 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).

[8]  B. Schölkopf,et al.  Towards Total Recall in Industrial Anomaly Detection , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Panagiotis I. Radoglou-Grammatikis,et al.  A Unified Deep Learning Anomaly Detection and Classification Approach for Smart Grid Environments , 2021, IEEE Transactions on Network and Service Management.

[10]  Tong Jia,et al.  NM-GAN: Noise-modulated generative adversarial network for video anomaly detection , 2021, Pattern Recognit..

[11]  R. Giryes,et al.  Autoencoders , 2021, Deep Learning in Science.

[12]  Zhiquan Qi,et al.  DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation , 2020, Neurocomputing.

[13]  Romaric Audigier,et al.  PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization , 2020, ICPR Workshops.

[14]  Emmanouil Panaousis,et al.  ARIES: A Novel Multivariate Intrusion Detection System for Smart Grid , 2020, Sensors.

[15]  Bodo Rosenhahn,et al.  Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows , 2020, 2021 IEEE Winter Conference on Applications of Computer Vision (WACV).

[16]  Ke Yu,et al.  LSTM-Based VAE-GAN for Time-Series Anomaly Detection , 2020, Sensors.

[17]  Dorit Merhof,et al.  Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[18]  Yedid Hoshen,et al.  Sub-Image Anomaly Detection with Deep Pyramid Correspondences , 2020, ArXiv.

[19]  Yedid Hoshen,et al.  Deep Nearest Neighbor Anomaly Detection , 2020, ArXiv.

[20]  Rajat Vikram Singh,et al.  Attention Guided Anomaly Localization in Images , 2019, ECCV.

[21]  Paul Bergmann,et al.  Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Hongbo Zhao,et al.  A Novel LSTM-GAN Algorithm for Time Series Anomaly Detection , 2019, 2019 Prognostics and System Health Management Conference (PHM-Qingdao).

[23]  Diederik P. Kingma,et al.  An Introduction to Variational Autoencoders , 2019, Found. Trends Mach. Learn..

[24]  Carsten Steger,et al.  MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Georg Langs,et al.  f‐AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks , 2019, Medical Image Anal..

[26]  Svetha Venkatesh,et al.  Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[27]  Cheng Cheng,et al.  A GAN-Based Anomaly Detection Approach for Imbalanced Industrial Time Series , 2019, IEEE Access.

[28]  Ramesh Nallapati,et al.  OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Toby P. Breckon,et al.  Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[30]  Lei Shi,et al.  MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks , 2019, ICANN.

[31]  Stanislav Pidhorskyi,et al.  Generative Probabilistic Novelty Detection with Adversarial Autoencoders , 2018, NeurIPS.

[32]  Carsten Steger,et al.  Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders , 2018, VISIGRAPP.

[33]  Toby P. Breckon,et al.  GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training , 2018, ACCV.

[34]  Mahmood Fathy,et al.  Adversarially Learned One-Class Classifier for Novelty Detection , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[35]  Paolo Napoletano,et al.  Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity , 2018, Sensors.

[36]  Vincent Dumoulin,et al.  Generative Adversarial Networks: An Overview , 2017, 1710.07035.

[37]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[38]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[40]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[41]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[42]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[43]  Ken Perlin,et al.  An image synthesizer , 1988 .

[44]  Draft,et al.  Introduction to Autoencoders , 2015 .