用扩散模型生成图像时，解决分布对齐和覆盖不足问题
PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion
- 用能量引导对齐真实数据分布，避免生成异常样本
- 通过多样化提示工程提升真实数据流形的覆盖度
- 适合需要高质量无数据知识蒸馏的大规模图像任务
数据自由知识蒸馏（DFKD）在不访问真实分布数据的情况下，将教师模型的知识传递给学生模型。现有方法在小规模图像上表现良好，但在合成大规模图像时易出现模式崩溃，导致知识迁移受限。近期利用先进生成模型合成逼真图像成为有前景的替代方案。然而，直接使用现成扩散模型生成数据面临精确率-召回率挑战：1）确保合成数据与真实分布一致；2）确保覆盖真实数据流形。为此，我们提出PRISM，一种基于精确率-召回率感知的合成方法。具体而言，引入能量引导分布对齐，避免生成分布外样本；设计多样化提示工程，增强真实数据流形的覆盖度。在多个大规模图像数据集上的大量实验表明PRISM具有显著优势。此外，经PRISM训练的模型展现出强域泛化能力。
原文摘要 · Abstract (English)
Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access to the real in-distribution (ID) data. While existing methods perform well on small-scale images, they suffer from mode collapse when synthesizing large-scale images, resulting in limited knowledge transfer. Recently, leveraging advanced generative models to synthesize photorealistic images has emerged as a promising alternative. Nevertheless, directly using off-the-shelf diffusion to generate datasets faces the precision-recall challenges: 1) ensuring synthetic data aligns with the real distribution, and 2) ensuring coverage of the real ID manifold. In response, we propose PRISM, a precision-recall informed synthesis method. Specifically, we introduce Energy-guided Distribution Alignment to avoid the generation of out-of-distribution samples, and design the Diversified Prompt Engineering to enhance coverage of the real ID manifold. Extensive experiments on various large-scale image datasets demonstrate the superiority of PRISM. Moreover, we demonstrate that models trained with PRISM exhibit strong domain generalization.
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。