Integration of deep generative Anomaly Detection algorithm in high-speed industrial line
Not on the map. Why?
Abstract (arXiv)
Industrial visual inspection in pharmaceutical production requires high accuracy under strict constraints on cycle time, hardware footprint, and operational cost. Manual inline inspection is still common, but it is affected by operator variability and limited throughput. Classical rule-based computer vision pipelines are often rigid and difficult to scale to highly variable production scenarios. To address these limitations, we present a semi-supervised anomaly detection framework based on a generative adversarial architecture with a residual autoencoder and a dense bottleneck, specifically designed for online deployment on a high-speed Blow-Fill-Seal (BFS) line. The model is trained only on nominal samples and detects anomalies through reconstruction residuals, providing both classification and spatial localization via heatmaps. The training set contains 2,815,200 grayscale patches. Experiments on a real industrial test kit show high detection performance while satisfying timing constraints compatible with a 500 ms acquisition slot.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 48 references that are in the map. First posted on arXiv 8 Mar 2026.
Builds on
29 of 48 references.
References · 29
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
- 2022Generative Adversarial Networkscited by 5,603
- 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
- 2016Density estimation using Real NVPcited by 2,029
- 2019An Introduction to Variational Autoencoderscited by 997
- 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
- 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
- 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
- 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
- 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
- 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
17 more
- 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 225
- 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
- 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
- 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 157
- 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
- 2020Deep Nearest Neighbor Anomaly Detectioncited by 103
- 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
- 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
- 2022Deep Isolation Forest for Anomaly Detectioncited by 90
- 2021Divide and Contrast: Self-supervised Learning from Uncurated Datacited by 85
- 2022Anomalib: A Deep Learning Library for Anomaly Detectioncited by 75
- 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
- 2019A Survey on GANs for Anomaly Detectioncited by 32
- 2020Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoderscited by 29
- 2023ViT-AE++: Improving Vision Transformer Autoencoder for Self-supervised Medical Image Representationscited by 12
- 2019Deep Residual Autoencoder for quality independent JPEG restorationcited by 3
- 2023A Probabilistic Transformation of Distance-Based Outlierscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.