用确定性点过程提升流模型采样多样性，少样本覆盖更多模式。
DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows
- 用确定性点过程设计样本耦合，驱动固定预算下的多样性
- 在少样本条件下实现更全面的模式覆盖，效果优于重复采样
- 适合文本引导图像生成、图像修复等需高效多样性的任务
许多真实世界中基于流的生成模型应用需要覆盖目标分布多个模式的多样化样本。然而，当前主流方法获取多样样本效率低，需从源分布独立采样大量样本并经流映射，直至达到期望的模式覆盖。为此，我们提出DiverseFlow：一种无需训练的多样化改进方法。核心思想是利用确定性点过程（determinantal point process）在固定采样预算下诱导样本间的耦合，从而提升多样性。本质上，DiverseFlow能在较少样本下探索流模型中的更多变体。我们在多义词引导的图像生成、大孔洞图像修复等反问题以及类别条件图像合成等任务中验证了该方法的有效性，证明其在样本效率与模式覆盖率之间实现了良好平衡。
原文摘要 · Abstract (English)
Many real-world applications of flow-based generative models desire a diverse set of samples that cover multiple modes of the target distribution. However, the predominant approach for obtaining diverse sets is not sample-efficient, as it involves independently obtaining many samples from the source distribution and mapping them through the flow until the desired mode coverage is achieved. As an alternative to repeated sampling, we introduce DiverseFlow: a training-free approach to improve the diversity of flow models. Our key idea is to employ a determinantal point process to induce a coupling between the samples that drives diversity under a fixed sampling budget. In essence, DiverseFlow allows exploration of more variations in a learned flow model with fewer samples. We demonstrate the efficacy of our method for tasks where sample-efficient diversity is desirable, such as text-guided image generation with polysemous words, inverse problems like large-hole inpainting, and class-conditional image synthesis.
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。