Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization

Abstract

We introduce a simple and intuitive self-supervision task, Natural Synthetic Anomalies (NSA), for training an end-to-end model for anomaly detection and localization using only normal training data. NSA integrates Poisson image editing to seamlessly blend scaled patches of various sizes from separate images. This creates a wide range of synthetic anomalies which are more similar to natural sub-image irregularities than previous data-augmentation strategies for self-supervised anomaly detection. We evaluate the proposed method using natural and medical images. Our experiments with the MVTec AD dataset show that a model trained to localize NSA anomalies generalizes well to detecting real-world a priori unknown types of manufacturing defects. Our method achieves an overall detection AUROC of 97.2 outperforming all previous methods that learn without the use of additional datasets. Code available at https://github.com/hmsch/natural-synthetic-anomalies.

Accepted to ECCV 2022

Cited by in corpus (8)

• Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
• A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
• Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images
• Domain knowledge-informed Synthetic fault sample generation with Health Data Map for cross-domain Planetary Gearbox Fault Diagnosis
• REB: Reducing Biases in Representation for Industrial Anomaly Detection
• FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
• Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection
• Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images