用噪声混合提升扩散模型图像增广效果，融合两类别特征生成自然高清图像。
NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
- 在扩散模型中混合两类图像的估计噪声实现跨类别融合。
- 分类实验表明性能优于传统增广与随机生成方法。
- 适合需要高质量图像增广的视觉分类任务研究者使用。
本文提出一种新型数据增广方法 NoiseCutMix，将 CutMix 思想引入扩散模型生成过程，结合不同类别的估计噪声以融合两类别特征，生成兼具自然性与高分辨率的图像。传统 CutMix 在跨类别拼接时易出现不自然边界，而 NoiseCutMix 通过在噪声空间操作，有效缓解该问题。我们在分类任务中对比了该方法与经典增广技术、使用 Stable Diffusion 的随机生成及二者组合的表现。结果表明，NoiseCutMix 显著提升模型性能，且生成图像质量更高。代码已开源：https://github.com/shumpei-takezaki/NoiseCutMix。
原文摘要 · Abstract (English)
In this study, we propose a novel data augmentation method that introduces the concept of CutMix into the generation process of diffusion models, thereby exploiting both the ability of diffusion models to generate natural and high-resolution images and the characteristic of CutMix, which combines features from two classes to create diverse augmented data. Representative data augmentation methods for combining images from multiple classes include CutMix and MixUp. However, techniques like CutMix often result in unnatural boundaries between the two images due to contextual differences. Therefore, in this study, we propose a method, called NoiseCutMix, to achieve natural, high-resolution image generation featuring the fused characteristics of two classes by partially combining the estimated noise corresponding to two different classes in a diffusion model. In the classification experiments, we verified the effectiveness of the proposed method by comparing it with conventional data augmentation techniques that combine multiple classes, random image generation using Stable Diffusion, and combinations of these methods. Our codes are available at: https://github.com/shumpei-takezaki/NoiseCutMix
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。