用数学公式生成干扰条纹图，提升模型抗真实退化能力
MoireDB: Formula-generated Interference-fringe Image Dataset
- 通过数学公式生成视觉干扰条纹图像，避免版权和绘制成本
- 在多种退化场景下，增强模型识别准确率，优于传统艺术图方法
- 适合需要低成本、可扩展数据增强的计算机视觉研究者
图像识别模型在应对真实世界退化时仍存在鲁棒性不足的问题。现有数据增强方法如PixMix依赖生成艺术和特征可视化（FVis），面临版权、绘制成本及可扩展性问题。本文提出MoireDB，一个基于公式生成的干涉条纹图像数据集，用于图像增强以提升鲁棒性。该方法消除版权隐患，降低数据构建成本，并通过错觉图案增强模型对真实退化的适应能力。实验表明，使用MoireDB增强的图像在多种退化条件下表现优于传统的分形艺术与FVis-based方法，证明其是一种高效且可扩展的鲁棒性提升方案。
原文摘要 · Abstract (English)
Image recognition models have struggled to treat recognition robustness to real-world degradations. In this context, data augmentation methods like PixMix improve robustness but rely on generative arts and feature visualizations (FVis), which have copyright, drawing cost, and scalability issues. We propose MoireDB, a formula-generated interference-fringe image dataset for image augmentation enhancing robustness. MoireDB eliminates copyright concerns, reduces dataset assembly costs, and enhances robustness by leveraging illusory patterns. Experiments show that MoireDB augmented images outperforms traditional Fractal arts and FVis-based augmentations, making it a scalable and effective solution for improving model robustness against real-world degradations.
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。