Corpus ID: 221370646

Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

  title={Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows},
  author={M. Rudolph and B. Wandt and B. Rosenhahn},
The detection of manufacturing errors is crucial in fabrication processes to ensure product quality and safety standards. Since many defects occur very rarely and their characteristics are mostly unknown a priori, their detection is still an open research question. To this end, we propose DifferNet: It leverages the descriptiveness of features extracted by convolutional neural networks to estimate their density using normalizing flows. Normalizing flows are well-suited to deal with low… Expand
3 Citations

Figures and Tables from this paper

Computer Vision and Normalizing Flow Based Defect Detection
  • Highly Influenced
  • PDF
CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
  • Highly Influenced
  • PDF
Perfect density models cannot guarantee anomaly detection
  • PDF


MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
  • 84
  • PDF
ADGAN: A Scalable GAN-based Architecture for Image Anomaly Detection
  • H. Cheng, H. Liu, F. Gao, Z. Chen
  • Computer Science
  • 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)
  • 2020
  • 1
Surface defect saliency of magnetic tile
  • Yibin Huang, C. Qiu, Kui Yuan
  • Computer Science
  • 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE)
  • 2018
  • 28
  • Highly Influential
f‐AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks
  • 152
GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
  • 226
  • PDF
Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes
  • 198
  • PDF
Very Deep Convolutional Networks for Large-Scale Image Recognition
  • 46,254
  • PDF
Deep Residual Learning for Image Recognition
  • 62,695
  • PDF