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

By Paul Bergmann, Michael Fauser, David Sattlegger, Carsten Steger. Computer Vision and Pattern Recognition, 2019

2,187 citations recorded by the source corpus.

The detection of anomalous structures in natural image data is of utmost importance for numerous tasks in the ﬁeld of computer vision. The development of methods for unsupervised anomaly detection requires data on which to train and evaluate new approaches and ideas. We introduce the MVTec Anomaly Detection (MVTec AD) dataset containing 5354 high-resolution color images of different object and texture categories. It contains normal, i.e., defect-free, images intended for training and images with anomalies intended for testing. The anomalies manifest themselves in the form of over 70 different types of defects such as scratches, dents, contaminations, and various structural changes. In addition, we provide pixel-precise ground truth regions for all anomalies. We also conduct a thorough evaluation of current state-of-the-art unsupervised anomaly detection methods based on deep architectures such as convolutional autoencoders, generative adversarial networks, and feature descriptors using pre-trained convolutional neural networks, as well as classical computer vision methods. This initial benchmark indicates that there is considerable room for improvement. To the best of our knowledge, this is the ﬁrst comprehensive, multi-object, multi-defect dataset for anomaly detection that provides pixel-accurate ground truth regions and focuses on real-world applications.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/3aa681914a7da79f7d7293f51a058eefe61c8bb7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

Citations in the corpus

CutPaste: Self-Supervised Learning for Anomaly Detection and Localization (2021, methodology): “Many problems from different vision applications are anomaly detection, including manufacturing defect detection [9, 5], medical image analysis [50, 48], and video surveillance [2, 31, 53].”
Multiresolution Knowledge Distillation for Anomaly Detection (2020, background): “MVTecAD [7]: an industrial dataset with over 5k high-resolution images in 15 categories of objects and textures.”
Uninformed Students: Student-Teacher Anomaly Detection With Discriminative Latent Embeddings (2019, methodology): “[7] provide benchmarks for several state-of-the-art algorithms and identify a large room for improvement.”
FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows (2021, methodology): “The experimental results in MVTec anomaly detection dataset (Bergmann et al. 2019) show that our method out-performs the previous state-of-the-art anomaly detection methods in both accuracy and reasoning efﬁciency.”
SimpleNet: A Simple Network for Image Anomaly Detection and Localization (2023, methodology): “The technique to detect the various anomalies of interest has a broad set of applications in industrial inspection [3, 6].”
CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization (2022, methodology): “We evaluated the proposed method using MVTec AD benchmark [1], which is a popular industrial image dataset for visual inspection.”
Mixed supervision for surface-defect detection: from weakly to fully supervised learning (2021, neutral): “The latter achieved state-of-the-art results in unsupervised anomaly detection on the MVTec dataset [3], which, however, only partially reﬂects the complexity of real-world industrial examples.”
AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models (2023, methodology): “To prove the efficacy of each proposed module, extensive ablation experiments are conducted on both the MVTec-AD and VisA datasets.”
PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation (2020, methodology): “[2] evaluated both a ADGAN and autoencoder approaches on MVTec dataset [2] finding complementary strengths.”
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection (2021, methodology): “The MVTec AD [5] data set is a standard benchmark for evaluating anomaly detection methods on industrial inspection images.”
Revisiting Reverse Distillation for Anomaly Detection (2023, methodology): “Quantitative comparison on different backbones on MVTec [4].”
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies (2023, methodology): “[7, 9] has catalyzed the development of methods for industrial applications.”
Student-Teacher Feature Pyramid Matching for Anomaly Detection (2021, methodology): “Simliar to typical autoencoders (AE) [7, 30] and variational autoencoders (VAE) [22], CAVGA also suffers from the strong generalization ability which allows good reconstruction for anomalous images.”
A Unified Model for Multi-class Anomaly Detection (2022, methodology): “All experiments are implemented on MVTec-AD [2] and evaluated with AUROC under the unified case.”