The scale and quality of a dataset significantly impact the performance of deep models. However, acquiring large-scale annotated datasets is both a costly and time-consuming endeavor. To address this challenge, dataset expansion technologies aim to automatically augment datasets, unlocking the full potential of deep models. Current data expansion methods encompass image transformation-based and synthesis-based methods. The transformation-based methods introduce only local variations, resulting in poor diversity. While image synthesis-based methods can create entirely new content, significantly enhancing informativeness. However, existing synthesis methods carry the risk of distribution deviations, potentially degrading model performance with out-of-distribution samples. In this paper, we propose DistDiff, an effective data expansion framework based on the distribution-aware diffusion model. DistDiff constructs hierarchical prototypes to approximate the real data distribution, optimizing latent data points within diffusion models with hierarchical energy guidance. We demonstrate its ability to generate distribution-consistent samples, achieving substantial improvements in data expansion tasks. Specifically, without additional training, DistDiff achieves a 30.7% improvement in accuracy across six image datasets compared to the model trained on original datasets and a 9.8% improvement compared to the state-of-the-art diffusion-based method. Our code is available at https://github.com/haoweiz23/DistDiff

翻译：数据集的规模与质量显著影响深度模型的性能。然而，获取大规模标注数据集既昂贵又耗时。为应对这一挑战，数据集扩充技术旨在自动增强数据集，以充分释放深度模型的潜力。当前的数据扩充方法包括基于图像变换和基于合成的方法。基于变换的方法仅引入局部变化，导致多样性不足；而基于图像合成的方法能生成全新内容，显著提升信息量。然而，现有合成方法存在分布偏差风险，可能因分布外样本导致模型性能下降。本文提出DistDiff——一种基于分布感知扩散模型的高效数据扩充框架。DistDiff构建分层原型以近似真实数据分布，并通过分层能量引导优化扩散模型中的潜在数据点。我们验证了其生成与分布一致样本的能力，在数据扩充任务中取得显著提升。具体而言，无需额外训练，DistDiff在六个图像数据集上相较于基于原始数据集训练的模型实现了30.7%的准确率提升，相较现有最先进的基于扩散的方法实现了9.8%的提升。我们的代码已开源至https://github.com/haoweiz23/DistDiff