用一张图生成多样真实图像，解决芯片检测数据少难题
SinSEMI: A One-Shot Image Generation Model and Data-Efficient Evaluation Framework for Semiconductor Inspection Equipment
- 基于多尺度流模型+感知相似性引导生成图像
- 仅用两张参考图即可全面评估生成效果
- 生成图像兼具高保真与多样性，适合训练AI
在半导体设备研发初期，获取大量原始光学图像面临巨大挑战，数据稀缺严重制约了AI解决方案的发展。为此，我们提出SinSEMI，一种新颖的一次性学习方法，可从单张光学图像生成多样且高度真实的图像。SinSEMI采用多尺度流模型，并在采样过程中引入LPIPS（Learned Perceptual Image Patch Similarity）能量引导，确保生成结果在感知真实性和输出多样性方面表现优异。我们还设计了一个专用于该场景的综合评估框架，仅需两幅参考图像即可实现全面评估。通过与多种一次性生成技术对比，实验表明SinSEMI在视觉质量、定量指标及下游任务中均表现更优。结果证明，SinSEMI生成的图像具备高保真度与有意义的多样性，可作为半导体AI应用的训练数据。
原文摘要 · Abstract (English)
In the early stages of semiconductor equipment development, obtaining large quantities of raw optical images poses a significant challenge. This data scarcity hinder the advancement of AI-powered solutions in semiconductor manufacturing. To address this challenge, we introduce SinSEMI, a novel one-shot learning approach that generates diverse and highly realistic images from single optical image. SinSEMI employs a multi-scale flow-based model enhanced with LPIPS (Learned Perceptual Image Patch Similarity) energy guidance during sampling, ensuring both perceptual realism and output variety. We also introduce a comprehensive evaluation framework tailored for this application, which enables a thorough assessment using just two reference images. Through the evaluation against multiple one-shot generation techniques, we demonstrate SinSEMI's superior performance in visual quality, quantitative measures, and downstream tasks. Our experimental results demonstrate that SinSEMI-generated images achieve both high fidelity and meaningful diversity, making them suitable as training data for semiconductor AI applications.
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。