用视觉表示引导扩散模型生成图像，提升训练数据质量与模型性能。
Representation-Conditioned Diffusion Models for Guided Training Data Generation
- 以DINOv2等模型的特征表示作为条件，生成图像。
- 合成数据训练模型在ImageNet100上比传统方法高10.76个百分点准确率。
- 生成图像可作数据增强，适合缺乏真实数据的视觉任务研究。
数据可用性仍是深度学习应用中的关键瓶颈。大规模数据集往往难以获取、整理和标注，限制了监督学习的可扩展性。本文评估了基于生成式深度学习合成图像数据集训练模型的分类性能。具体地，采用以DINOv2、DINOv3和CLIP学习到的表示为条件的潜在扩散模型。结果表明，该表示条件化方法相比类别条件生成显著提升性能（在ImageNet100上顶1准确率提高10.76个百分点），并改善了样本质量和模式覆盖度。通过扩大合成数据规模，其性能甚至超过使用真实数据训练的分类器（顶1准确率高出2.0个百分点）。我们还展示了生成图像可用于数据增强，优于传统方法；且可通过条件空间进行样本筛选，进一步提升训练价值。这些发现表明，表示条件化扩散模型为大规模视觉学习任务中的数据补充、替代提供了可行路径。
原文摘要 · Abstract (English)
Data availability remains a critical bottleneck in many deep learning applications. Large-scale datasets are often expensive to collect, curate and annotate, which can limit the scalability and applicability of supervised learning methods. In this work, we evaluate the classification performance of models trained on synthetic image datasets produced by generative deep learning. In particular, we use latent diffusion models conditioned on learned representations from DINOv2, DINOv3, and CLIP. Our results demonstrates that this representation-conditioned formulation significantly outperforms class-conditioned generation by a large margin (+10.76 p.p. top-1 accuracy on ImageNet100), by improving sample quality and mode coverage. Furthermore, by scaling the size of the synthetic dataset, we are able to outperform a classifier trained on the real data (+2.0 p.p top-1 accuracy). We also demonstrate how generated images can be used for augmentation purposes, outperforming classical augmentation methods, and how the conditioning space can be used for sample filtering to further improve training value. Collectively, these findings highlight that representation-conditioned diffusion models provide a promising approach for augmenting, complementing, or potentially replacing real-world datasets in large-scale visual learning tasks.
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。