mlsanityData to 14 Oct 2026

SinSEMI: A One-Shot Image Generation Model and Data-Efficient Evaluation Framework for Semiconductor Inspection Equipment

arXiv 2511.06740 ↗First posted 10 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

20 of 29 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  6. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  7. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  8. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 294
  9. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 273
  10. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  11. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  12. 2020Improved Techniques for Training Single-Image GANscited by 78
8 more
  1. 2022SinDDM: A Single Image Denoising Diffusion Modelcited by 60
  2. 2022SinFusion: Training Diffusion Models on a Single Image or Videocited by 58
  3. 2021Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Modelscited by 51
  4. 2022SinDiffusion: Learning a Diffusion Model from a Single Natural Imagecited by 42
  5. 2022Generating natural images with direct Patch Distributions Matchingcited by 27
  6. 2022Few-shot Image Generation with Diffusion Modelscited by 21
  7. 2022Deep Learning-Based Defect Classification and Detection in SEM Imagescited by 14
  8. 2024Addressing Class Imbalance and Data Limitations in Advanced Node Semiconductor Defect Inspection: A Generative Approach for SEM Imagescited by 5

Built on by

Not cited yet.