Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908828429189120 |
|---|---|
| author | Zhu, Wenbing Wang, Chengjie Gao, Bin-Bin Zhang, Jiangning Jiang, Guannan Hu, Jie Gan, Zhenye Wang, Lidong Zhou, Ziqing Zhang, Jianghui Cheng, Linjie Pan, Yurui Peng, Bo Chi, Mingmin Ma, Lizhuang |
| author_facet | Zhu, Wenbing Wang, Chengjie Gao, Bin-Bin Zhang, Jiangning Jiang, Guannan Hu, Jie Gan, Zhenye Wang, Lidong Zhou, Ziqing Zhang, Jianghui Cheng, Linjie Pan, Yurui Peng, Bo Chi, Mingmin Ma, Lizhuang |
| contents | Industrial Anomaly Detection (IAD) is a cornerstone for ensuring operational safety, maintaining product quality, and optimizing manufacturing efficiency. However, the advancement of IAD algorithms is severely hindered by the limitations of existing public benchmarks. Current datasets often suffer from restricted category diversity and insufficient scale, leading to performance saturation and poor model transferability in complex, real-world scenarios. To bridge this gap, we introduce Real-IAD Variety, the largest and most diverse IAD benchmark. It comprises 198,950 high-resolution images across 160 distinct object categories. The dataset ensures unprecedented diversity by covering 28 industries, 24 material types, 22 color variations, and 27 defect types. Our extensive experimental analysis highlights the substantial challenges posed by this benchmark: state-of-the-art multi-class unsupervised anomaly detection methods suffer significant performance degradation (ranging from 10% to 20%) when scaled from 30 to 160 categories. Conversely, we demonstrate that zero-shot and few-shot IAD models exhibit remarkable robustness to category scale-up, maintaining consistent performance and significantly enhancing generalization across diverse industrial contexts. This unprecedented scale positions Real-IAD Variety as an essential resource for training and evaluating next-generation foundation IAD models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00540 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era Zhu, Wenbing Wang, Chengjie Gao, Bin-Bin Zhang, Jiangning Jiang, Guannan Hu, Jie Gan, Zhenye Wang, Lidong Zhou, Ziqing Zhang, Jianghui Cheng, Linjie Pan, Yurui Peng, Bo Chi, Mingmin Ma, Lizhuang Computer Vision and Pattern Recognition Industrial Anomaly Detection (IAD) is a cornerstone for ensuring operational safety, maintaining product quality, and optimizing manufacturing efficiency. However, the advancement of IAD algorithms is severely hindered by the limitations of existing public benchmarks. Current datasets often suffer from restricted category diversity and insufficient scale, leading to performance saturation and poor model transferability in complex, real-world scenarios. To bridge this gap, we introduce Real-IAD Variety, the largest and most diverse IAD benchmark. It comprises 198,950 high-resolution images across 160 distinct object categories. The dataset ensures unprecedented diversity by covering 28 industries, 24 material types, 22 color variations, and 27 defect types. Our extensive experimental analysis highlights the substantial challenges posed by this benchmark: state-of-the-art multi-class unsupervised anomaly detection methods suffer significant performance degradation (ranging from 10% to 20%) when scaled from 30 to 160 categories. Conversely, we demonstrate that zero-shot and few-shot IAD models exhibit remarkable robustness to category scale-up, maintaining consistent performance and significantly enhancing generalization across diverse industrial contexts. This unprecedented scale positions Real-IAD Variety as an essential resource for training and evaluating next-generation foundation IAD models. |
| title | Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.00540 |