arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.01490cs.CVcs.AIcs.LG
收藏

MoireDB:公式生成的干涉条纹图像数据集

MoireDB: Formula-generated Interference-fringe Image Dataset

Tokyo Denki University(东京电机大学);National Institute of Advanced Industrial Science and Technology (AIST)(独立行政法人产业技术综合研究所);University of Oxford(牛津大学)

Yuto Matsuo, Ryo Hayamizu, Hirokatsu Kataoka, Akio Nakamura

AI总结:

针对图像识别模型在真实世界退化下鲁棒性不足及现有数据增强方法的版权与成本问题,提出公式生成的干涉条纹图像数据集MoireDB,通过错觉图案有效提升模型鲁棒性且优于传统方法。

摘要:

图像识别模型一直难以实现对真实世界退化的识别鲁棒性。在此背景下,像PixMix这样的数据增强方法提升了鲁棒性,但依赖于生成艺术和特征可视化(FVis),这存在版权、绘制成本和可扩展性问题。我们提出了MoireDB,一个公式生成的干涉条纹图像数据集,用于增强鲁棒性的图像增强。MoireDB消除了版权问题,降低了数据集组装成本,并通过利用错觉图案增强鲁棒性。实验表明,MoireDB增强的图像优于传统的Fractal艺术和基于FVis的增强,使其成为提升模型对真实世界退化鲁棒性的可扩展且有效的解决方案。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑