用域适应技术减少半导体缺陷分类的标注成本
Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturing
- 基于CycleGAN改进，引入新损失函数提升跨域泛化能力
- 在真实电子显微镜图像上验证，半监督/无监督场景均有效
- 适合需要快速部署且标注资源有限的工业质检场景
在半导体领域，市场需求高且竞争激烈，上市速度与产品质量是赢得市场份额的关键。近年来，深度学习在计算机视觉领域的成功推动了工业4.0/5.0中缺陷分类等应用的发展。其中，域适应（DA）通过利用源域知识迁移到目标域，在无需大量重新标注或训练的情况下提升模型鲁棒性与可扩展性，显著降低计算与人力成本，使专家能聚焦高价值任务。本文在半导体缺陷分类场景下，测试了半监督与无监督域适应方法的有效性，并提出DBACS方法——一种受CycleGAN启发、并加入额外损失项的改进模型。所有方法均在真实电子显微镜图像数据集上进行验证，结果表明该方法在无监督与半监督设置下均具有效性，为半导体领域域适应技术的发展提供了实用方案。
原文摘要 · Abstract (English)
In the semiconductor sector, due to high demand but also strong and increasing competition, time to market and quality are key factors in securing significant market share in various application areas. Thanks to the success of deep learning methods in recent years in the computer vision domain, Industry 4.0 and 5.0 applications, such as defect classification, have achieved remarkable success. In particular, Domain Adaptation (DA) has proven highly effective since it focuses on using the knowledge learned on a (source) domain to adapt and perform effectively on a different but related (target) domain. By improving robustness and scalability, DA minimizes the need for extensive manual re-labeling or re-training of models. This not only reduces computational and resource costs but also allows human experts to focus on high-value tasks. Therefore, we tested the efficacy of DA techniques in semi-supervised and unsupervised settings within the context of the semiconductor field. Moreover, we propose the DBACS approach, a CycleGAN-inspired model enhanced with additional loss terms to improve performance. All the approaches are studied and validated on real-world Electron Microscope images considering the unsupervised and semi-supervised settings, proving the usefulness of our method in advancing DA techniques for the semiconductor field.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。