用通用文生图模型实现无需训练的图像数据集蒸馏，性能超越现有方法。
CoDA: From Text-to-Image Diffusion Models to Training-Free Dataset Distillation
- 通过密度发现机制识别目标数据集的核心分布，指导生成过程对齐。
- 在ImageNet-1K上50张/类设置下达到60.4%新高准确率，无需目标专用模型训练。
- 适用于无额外训练成本的高效数据蒸馏，适合资源受限场景。
当前基于生成模型的数据集蒸馏（DD）方法面临两大根本限制：一是虽开创性使用扩散模型并取得优异效果，但多数方法仍需在完整目标数据集上预训练扩散模型，违背了数据蒸馏初衷且成本高昂；二是部分方法采用通用文生图模型，但因其蕴含的通用先验与目标数据语义存在显著分布偏差，导致性能不佳。为此，我们提出核心分布对齐（CoDA）框架，仅依赖现成的文生图模型即可实现有效蒸馏。核心思路是先通过鲁棒的密度发现机制识别目标数据集的‘内在核心分布’，再引导生成过程使其与该核心分布对齐。由此，CoDA有效弥合通用生成先验与目标语义之间的鸿沟，生成高度代表性的蒸馏数据集。大量实验表明，即使不依赖针对目标数据集训练的生成模型，CoDA在所有基准测试中性能均达到或优于以往依赖目标训练的方法，包括ImageNet-1K及其子集。尤其在ImageNet-1K的50张/类设置下，创下60.4%的新最优准确率。代码已公开于项目主页：https://github.com/zzzlt422/CoDA。
原文摘要 · Abstract (English)
Prevailing Dataset Distillation (DD) methods leveraging generative models confront two fundamental limitations. First, despite pioneering the use of diffusion models in DD and delivering impressive performance, the vast majority of approaches paradoxically require a diffusion model pre-trained on the full target dataset, undermining the very purpose of DD and incurring prohibitive training costs. Second, although some methods turn to general text-to-image models without relying on such target-specific training, they suffer from a significant distributional mismatch, as the web-scale priors encapsulated in these foundation models fail to faithfully capture the target-specific semantics, leading to suboptimal performance. To tackle these challenges, we propose Core Distribution Alignment (CoDA), a framework that enables effective DD using only an off-the-shelf text-to-image model. Our key idea is to first identify the "intrinsic core distribution" of the target dataset using a robust density-based discovery mechanism. We then steer the generative process to align the generated samples with this core distribution. By doing so, CoDA effectively bridges the gap between general-purpose generative priors and target semantics, yielding highly representative distilled datasets. Extensive experiments suggest that, without relying on a generative model specifically trained on the target dataset, CoDA achieves performance on par with or even superior to previous methods with such reliance across all benchmarks, including ImageNet-1K and its subsets. Notably, it establishes a new state-of-the-art accuracy of 60.4% at the 50-images-per-class (IPC) setup on ImageNet-1K. Our code is available on the project webpage: https://github.com/zzzlt422/CoDA
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。