用生成AI增强图像数据，保留主体真实、背景多样，准确率提升超20%。
Data Augmentation for Image Classification using Generative AI
- 融合大模型与扩散模型，分步提取主体并生成多样化背景
- 在ImageNet等数据集上，分布内/外数据准确率分别提升15.6%和23.5%
- 适合需要高质量数据增强的视觉任务研究者使用
规模定律表明，人工智能模型性能与可用数据量成正比。数据增强是扩展数据集规模的可行方案。传统方法依赖旋转、平移和缩放等操作；近期方法利用生成式AI提升数据多样性，但常出现主体失真或引入无关伪影。本文提出自动化生成数据增强（AGA）框架，结合大语言模型（LLMs）、扩散模型与分割模型实现数据增强。AGA在保持前景真实性的同时保障背景多样性。具体贡献包括：(i) 基于分割与类别层次的物体提取；(ii) 通过提示分解实现组合复杂度的提示多样性；(iii) 仿射变换下的主体操控。我们在ImageNet、CUB和iWildCam三个代表性数据集上评估了AGA，实验结果表明，相比基线模型，其对分布内与分布外数据的准确率分别提升15.6%和23.5%，SIC评分提升64.3%。
原文摘要 · Abstract (English)
Scaling laws dictate that the performance of AI models is proportional to the amount of available data. Data augmentation is a promising solution to expanding the dataset size. Traditional approaches focused on augmentation using rotation, translation, and resizing. Recent approaches use generative AI models to improve dataset diversity. However, the generative methods struggle with issues such as subject corruption and the introduction of irrelevant artifacts. In this paper, we propose the Automated Generative Data Augmentation (AGA). The framework combines the utility of large language models (LLMs), diffusion models, and segmentation models to augment data. AGA preserves foreground authenticity while ensuring background diversity. Specific contributions include: i) segment and superclass based object extraction, ii) prompt diversity with combinatorial complexity using prompt decomposition, and iii) affine subject manipulation. We evaluate AGA against state-of-the-art (SOTA) techniques on three representative datasets, ImageNet, CUB, and iWildCam. The experimental evaluation demonstrates an accuracy improvement of 15.6% and 23.5% for in and out-of-distribution data compared to baseline models, respectively. There is also a 64.3% improvement in SIC score compared to the baselines.
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。