Evaluating Modern Visual Anomaly Detection Approaches in Semiconductor Manufacturing: A Comparative Study
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913832765489152 |
|---|---|
| author | Barusco, Manuel Borsatti, Francesco Khalifa, Youssef Ben Pezze, Davide Dalle Susto, Gian Antonio |
| author_facet | Barusco, Manuel Borsatti, Francesco Khalifa, Youssef Ben Pezze, Davide Dalle Susto, Gian Antonio |
| contents | Semiconductor manufacturing is a complex, multistage process. Automated visual inspection of Scanning Electron Microscope (SEM) images is indispensable for minimizing equipment downtime and containing costs. Most previous research considers supervised approaches, assuming a sufficient number of anomalously labeled samples. On the contrary, Visual Anomaly Detection (VAD), an emerging research domain, focuses on unsupervised learning, avoiding the costly defect collection phase while providing explanations of the predictions. We introduce a benchmark for VAD in the semiconductor domain by leveraging the MIIC dataset. Our results demonstrate the efficacy of modern VAD approaches in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07576 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Modern Visual Anomaly Detection Approaches in Semiconductor Manufacturing: A Comparative Study Barusco, Manuel Borsatti, Francesco Khalifa, Youssef Ben Pezze, Davide Dalle Susto, Gian Antonio Computer Vision and Pattern Recognition Artificial Intelligence Semiconductor manufacturing is a complex, multistage process. Automated visual inspection of Scanning Electron Microscope (SEM) images is indispensable for minimizing equipment downtime and containing costs. Most previous research considers supervised approaches, assuming a sufficient number of anomalously labeled samples. On the contrary, Visual Anomaly Detection (VAD), an emerging research domain, focuses on unsupervised learning, avoiding the costly defect collection phase while providing explanations of the predictions. We introduce a benchmark for VAD in the semiconductor domain by leveraging the MIIC dataset. Our results demonstrate the efficacy of modern VAD approaches in this field. |
| title | Evaluating Modern Visual Anomaly Detection Approaches in Semiconductor Manufacturing: A Comparative Study |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.07576 |