SEM-CLIP 2.0: Precise Zero-/Few-Shot Learning for Nanoscale Defect Detection in SEM Image
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · 2026-11 · 45 (11) · 6392-6405
DOI: 10.1109/tcad.2026.3663889 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2026-11. Verfasst von Qian Jin und 8 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: NSFC.
Abstract (Originalsprache)
In integrated circuit manufacturing, detecting and classifying stochastic morphological wafer surface defects is crucial for root cause analysis and yield enhancement. Complex background patterns in scanning electron microscopy (SEM) images and diverse defect textures pose significant challenges. Traditional methods usually suffer from insufficient data, labels, and poor transferability. In this article, we propose a novel zero-/few-shot learning approach, SEM-CLIP 2.0, based on our SEM-CLIP framework, for accurate defect classification and segmentation. By leveraging learnable text prompts, SEM-CLIP 2.0 fully utilizes large-scale external data sources to facilitate robust cross-domain knowledge transfer. It also customizes the contrastive language-image pretraining (CLIP) model to better focus on defect areas and minimize background distractions, thereby enhancing segmentation accuracy. Furthermore, our approach employs discriminative feature learning for open-set classification, facilitating more effective defect classification and enabling the detection of unknown defect categories. By alleviating the need for manual prompt engineering and extensive data annotation, SEM-CLIP 2.0 significantly reduces labor costs. Extensive experimental results demonstrate that our model achieves impressive classification and segmentation results under zero-/few-shot learning scenarios.
Förderung
- NSFC
Zitieren
APA
Jin, Q., Li, R., Jiang, Y., Liu, Y., Lu, X., Chen, Y., Gao, D., Sun, Q., & Zhuo, C. (2026). SEM-CLIP 2.0: Precise Zero-/Few-Shot Learning for Nanoscale Defect Detection in SEM Image. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 45(11), 6392-6405. https://doi.org/10.1109/tcad.2026.3663889
Vancouver
Jin Q, Li R, Jiang Y, Liu Y, Lu X, Chen Y, et al. SEM-CLIP 2.0: Precise Zero-/Few-Shot Learning for Nanoscale Defect Detection in SEM Image. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2026;45(11):6392-6405. doi:10.1109/tcad.2026.3663889
BibTeX
@article{Jin2026,
author = {Jin, Qian and Li, Ruidong and Jiang, Yuqi and Liu, Yumeng and Lu, Xudong and Chen, Yining and Gao, Dawei and Sun, Qi and Zhuo, Cheng},
title = {SEM-CLIP 2.0: Precise Zero-/Few-Shot Learning for Nanoscale Defect Detection in SEM Image},
journal = {IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems},
year = {2026},
volume = {45},
number = {11},
pages = {6392--6405},
doi = {10.1109/tcad.2026.3663889}
}
EUVIMED