{"ID":2891279,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.17359","arxiv_id":"2507.17359","title":"Exploring Active Learning for Semiconductor Defect Segmentation","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.17359","url_pdf":"https://arxiv.org/pdf/2507.17359v1","authors":"[\"Lile Cai\",\"Ramanpreet Singh Pahwa\",\"Xun Xu\",\"Jie Wang\",\"Richard Chang\",\"Lining Zhang\",\"Chuan-Sheng Foo\"]","published":"2025-07-23T09:44:11Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}