Exploring Active Learning for Semiconductor Defect Segmentation
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_ | 1866916858748207104 |
|---|---|
| author | Cai, Lile Pahwa, Ramanpreet Singh Xu, Xun Wang, Jie Chang, Richard Zhang, Lining Foo, Chuan-Sheng |
| author_facet | Cai, Lile Pahwa, Ramanpreet Singh Xu, Xun Wang, Jie Chang, Richard Zhang, Lining Foo, Chuan-Sheng |
| contents | The development of X-Ray microscopy (XRM) technology has enabled non-destructive inspection of semiconductor structures for defect identification. Deep learning is widely used as the state-of-the-art approach to perform visual analysis tasks. However, deep learning based models require large amount of annotated data to train. This can be time-consuming and expensive to obtain especially for dense prediction tasks like semantic segmentation. In this work, we explore active learning (AL) as a potential solution to alleviate the annotation burden. We identify two unique challenges when applying AL on semiconductor XRM scans: large domain shift and severe class-imbalance. To address these challenges, we propose to perform contrastive pretraining on the unlabelled data to obtain the initialization weights for each AL cycle, and a rareness-aware acquisition function that favors the selection of samples containing rare classes. We evaluate our method on a semiconductor dataset that is compiled from XRM scans of high bandwidth memory structures composed of logic and memory dies, and demonstrate that our method achieves state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17359 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Active Learning for Semiconductor Defect Segmentation Cai, Lile Pahwa, Ramanpreet Singh Xu, Xun Wang, Jie Chang, Richard Zhang, Lining Foo, Chuan-Sheng Computer Vision and Pattern Recognition The development of X-Ray microscopy (XRM) technology has enabled non-destructive inspection of semiconductor structures for defect identification. Deep learning is widely used as the state-of-the-art approach to perform visual analysis tasks. However, deep learning based models require large amount of annotated data to train. This can be time-consuming and expensive to obtain especially for dense prediction tasks like semantic segmentation. In this work, we explore active learning (AL) as a potential solution to alleviate the annotation burden. We identify two unique challenges when applying AL on semiconductor XRM scans: large domain shift and severe class-imbalance. To address these challenges, we propose to perform contrastive pretraining on the unlabelled data to obtain the initialization weights for each AL cycle, and a rareness-aware acquisition function that favors the selection of samples containing rare classes. We evaluate our method on a semiconductor dataset that is compiled from XRM scans of high bandwidth memory structures composed of logic and memory dies, and demonstrate that our method achieves state-of-the-art performance. |
| title | Exploring Active Learning for Semiconductor Defect Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.17359 |