PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916639713263616 |
|---|---|
| author | Pan, Yurui Wang, Lidong Chen, Yuchao Zhu, Wenbing Peng, Bo Chi, Mingmin |
| author_facet | Pan, Yurui Wang, Lidong Chen, Yuchao Zhu, Wenbing Peng, Bo Chi, Mingmin |
| contents | In industrial anomaly detection (IAD), accurately identifying defects amidst diverse anomalies and under varying imaging conditions remains a significant challenge. Traditional approaches often struggle with high false-positive rates, frequently misclassifying normal shadows and surface deformations as defects, an issue that becomes particularly pronounced in products with complex and intricate surface features. To address these challenges, we introduce PA-CLIP, a zero-shot anomaly detection method that reduces background noise and enhances defect detection through a pseudo-anomaly-based framework. The proposed method integrates a multiscale feature aggregation strategy for capturing detailed global and local information, two memory banks for distinguishing background information, including normal patterns and pseudo-anomalies, from true anomaly features, and a decision-making module designed to minimize false positives caused by environmental variations while maintaining high defect sensitivity. Demonstrated on the MVTec AD and VisA datasets, PA-CLIP outperforms existing zero-shot methods, providing a robust solution for industrial defect detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01292 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness Pan, Yurui Wang, Lidong Chen, Yuchao Zhu, Wenbing Peng, Bo Chi, Mingmin Computer Vision and Pattern Recognition In industrial anomaly detection (IAD), accurately identifying defects amidst diverse anomalies and under varying imaging conditions remains a significant challenge. Traditional approaches often struggle with high false-positive rates, frequently misclassifying normal shadows and surface deformations as defects, an issue that becomes particularly pronounced in products with complex and intricate surface features. To address these challenges, we introduce PA-CLIP, a zero-shot anomaly detection method that reduces background noise and enhances defect detection through a pseudo-anomaly-based framework. The proposed method integrates a multiscale feature aggregation strategy for capturing detailed global and local information, two memory banks for distinguishing background information, including normal patterns and pseudo-anomalies, from true anomaly features, and a decision-making module designed to minimize false positives caused by environmental variations while maintaining high defect sensitivity. Demonstrated on the MVTec AD and VisA datasets, PA-CLIP outperforms existing zero-shot methods, providing a robust solution for industrial defect detection. |
| title | PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.01292 |