ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defects

Abstract

Automatic visual inspection using machine learning plays a key role in achieving zero-defect policies in industry. Research on anomaly detection is constrained by the availability of datasets that capture complex defect appearances and imperfect imaging conditions, which are typical of production processes. Recent benchmarks indicate that most publicly available datasets are biased towards optimal imaging conditions, leading to an overestimation of their applicability in real-world industrial scenarios. To address this gap, we introduce the Industrial Screen Printing Anomaly Detection Dataset (ISP-AD). It presents challenging small and weakly contrasted surface defects embedded within structured patterns exhibiting high permitted design variability. To the best of our knowledge, it is the largest publicly available industrial dataset to date, including both synthetic and real defects collected directly from the factory floor. Beyond benchmarking recent unsupervised anomaly detection methods, experiments on a mixed supervised training strategy, incorporating both synthesized and real defects, were conducted. Experiments show that even a small amount of injected, weakly labeled real defects improves generalization. Furthermore, starting from training on purely synthetic defects, emerging real defective samples can be efficiently integrated into subsequent scalable training. Overall, our findings indicate that model-free synthetic defects can provide a cold-start baseline, whereas a small number of injected real defects refine the decision boundary for previously unseen defect characteristics. The presented unsupervised and supervised dataset splits are designed to emphasize research on unsupervised, self-supervised, and supervised approaches, enhancing their applicability to industrial settings.

36 pages, 8 figures, Accepted for publication in the Journal of Intelligent Manufacturing, the dataset is available at https://doi.org/10.5281/zenodo.14911042, the GitHub repository is available at https://github.com/p4ulk/isp-ad

References in corpus (17)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• A Unifying Review of Deep and Shallow Anomaly Detection
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• Deep Industrial Image Anomaly Detection: A Survey
• Mixed supervision for surface-defect detection: from weakly to fully supervised learning
• FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
• Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization
• A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• Generative adversarial network with object detector discriminator for enhanced defect detection on ultrasonic B-scans
• BlenderProc
• Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
• Distillation-based fabric anomaly detection
• Anomaly Detection for Industrial Applications, Its Challenges, Solutions, and Future Directions: A Review
• "Stones from Other Hills can Polish Jade": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injection
• AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis