A Curated List of Awesome Unsupervised Anomaly Detection on MVTec AD Dataset

Table of Contents

• 1. What is MVTec AD Dataset?
• 2. Awesome Unsupervised Anomaly Detection
• 3. Tsundoku
• 4. Contacts

1. What is MVTec AD Dataset?

MVTec AD dataset is the most popular dataset for evaluating unsupervised anomaly detection. It contains 5354 high-resolution color images of different object and texture categories. Each category contains defect-free images for training and defect images for testing.

MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

2. Awesome Unsupervised Anomaly Detection

• uninformed students: student-teacher anomaly detection with discriminative latent embeddings
• reconstruction by inpainting for visual anomaly detection
• sub-image anomaly detection with deep pyramid correspondences
• modeling the distribution of normal data in pre-trained deep features for anomaly detection
• DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
• Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

3. Tsundoku

• detecting road obstacles by erasing them

4. Contacts

• github: https://github.com/taikiinoue45/
• twitter: https://twitter.com/taikiinoue45/
• linkedin: https://www.linkedin.com/in/taikiinoue45/