TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Natural Synthetic Anomalies for Self-Supervised Anomaly De...

Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization

Hannah M. Schlüter, Jeremy Tan, Benjamin Hou, Bernhard Kainz

2021-09-30Data AugmentationAnomaly SegmentationAnomaly DetectionOut-of-Distribution DetectionSupervised Anomaly DetectionSelf-Supervised Anomaly DetectionAnomaly Classification
PaperPDFCodeCode(official)Code

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.

Results

TaskDatasetMetricValueModel
Anomaly DetectionAeBAD-VDetection AUROC64.6NSA
Anomaly DetectionAeBAD-SDetection AUROC56.7NSA
Anomaly DetectionAeBAD-SSegmentation AUPRO45.9NSA
Anomaly DetectionMVTec ADDetection AUROC97.2NSA
Anomaly DetectionMVTec ADSegmentation AUPRO91NSA
Anomaly DetectionMVTec ADSegmentation AUROC96.3NSA
Anomaly DetectionGoodsADAUPR71.8NSA
Anomaly DetectionGoodsADAUROC67.3NSA
2D ClassificationGoodsADAUPR71.8NSA
2D ClassificationGoodsADAUROC67.3NSA
Anomaly ClassificationGoodsADAUPR71.8NSA
Anomaly ClassificationGoodsADAUROC67.3NSA

Related Papers

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems2025-07-21Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management2025-07-17Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images2025-07-173DKeyAD: High-Resolution 3D Point Cloud Anomaly Detection via Keypoint-Guided Point Clustering2025-07-17A Semi-Supervised Learning Method for the Identification of Bad Exposures in Large Imaging Surveys2025-07-17Similarity-Guided Diffusion for Contrastive Sequential Recommendation2025-07-16A Privacy-Preserving Framework for Advertising Personalization Incorporating Federated Learning and Differential Privacy2025-07-16Data Augmentation in Time Series Forecasting through Inverted Framework2025-07-15