Saved in:
Bibliographic Details
Main Authors: Heckler-Kram, Lars, Neudeck, Jan-Hendrik, Scheler, Ulla, König, Rebecca, Steger, Carsten
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.21622
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914380336070656
author Heckler-Kram, Lars
Neudeck, Jan-Hendrik
Scheler, Ulla
König, Rebecca
Steger, Carsten
author_facet Heckler-Kram, Lars
Neudeck, Jan-Hendrik
Scheler, Ulla
König, Rebecca
Steger, Carsten
contents In recent years, performance on existing anomaly detection benchmarks like MVTec AD and VisA has started to saturate in terms of segmentation AU-PRO, with state-of-the-art models often competing in the range of less than one percentage point. This lack of discriminatory power prevents a meaningful comparison of models and thus hinders progress of the field, especially when considering the inherent stochastic nature of machine learning results. We present MVTec AD 2, a collection of eight anomaly detection scenarios with more than 8000 high-resolution images. It comprises challenging and highly relevant industrial inspection use cases that have not been considered in previous datasets, including transparent and overlapping objects, dark-field and back light illumination, objects with high variance in the normal data, and extremely small defects. We provide comprehensive evaluations of state-of-the-art methods and show that their performance remains below 60% average AU-PRO. Additionally, our dataset provides test scenarios with lighting condition changes to assess the robustness of methods under real-world distribution shifts. We host a publicly accessible evaluation server that holds the pixel-precise ground truth of the test set (https://benchmark.mvtec.com/). All image data is available at https://www.mvtec.com/company/research/datasets/mvtec-ad-2.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21622
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detection
Heckler-Kram, Lars
Neudeck, Jan-Hendrik
Scheler, Ulla
König, Rebecca
Steger, Carsten
Computer Vision and Pattern Recognition
In recent years, performance on existing anomaly detection benchmarks like MVTec AD and VisA has started to saturate in terms of segmentation AU-PRO, with state-of-the-art models often competing in the range of less than one percentage point. This lack of discriminatory power prevents a meaningful comparison of models and thus hinders progress of the field, especially when considering the inherent stochastic nature of machine learning results. We present MVTec AD 2, a collection of eight anomaly detection scenarios with more than 8000 high-resolution images. It comprises challenging and highly relevant industrial inspection use cases that have not been considered in previous datasets, including transparent and overlapping objects, dark-field and back light illumination, objects with high variance in the normal data, and extremely small defects. We provide comprehensive evaluations of state-of-the-art methods and show that their performance remains below 60% average AU-PRO. Additionally, our dataset provides test scenarios with lighting condition changes to assess the robustness of methods under real-world distribution shifts. We host a publicly accessible evaluation server that holds the pixel-precise ground truth of the test set (https://benchmark.mvtec.com/). All image data is available at https://www.mvtec.com/company/research/datasets/mvtec-ad-2.
title The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.21622