无需引导机制，用简单两步提升扩散模型生成少数类样本能力
Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation
- 通过方差增强初始化和时间步跳过实现无引导生成
- 生成效果媲美先进引导方法，计算量大幅降低
- 适合数据稀缺场景下的生成任务，如医疗图像合成
少数类样本是数据流形低密度区域中的稀有实例，在数据增强、创意内容生成等生成式AI应用中具有重要价值。然而，现有基于扩散模型的少数类生成方法通常依赖计算成本高昂的专门引导机制。为此，本文提出一种简单而强大的无引导方法Boost-and-Skip，仅需对标准生成过程做两项最小改动：(i) 方差增强初始化，(ii) 时间步跳过。我们证明这些看似简单的调整具备坚实的理论与实证支持，能有效促进未充分表示的少数类特征涌现。全面实验表明，Boost-and-Skip显著提升了生成少数类样本的能力，即使在计算开销极低的情况下，仍可媲美基于引导的最先进方法。代码已公开于https://github.com/soobin-um/BnS。
原文摘要 · Abstract (English)
Minority samples are underrepresented instances located in low-density regions of a data manifold, and are valuable in many generative AI applications, such as data augmentation, creative content generation, etc. Unfortunately, existing diffusion-based minority generators often rely on computationally expensive guidance dedicated for minority generation. To address this, here we present a simple yet powerful guidance-free approach called Boost-and-Skip for generating minority samples using diffusion models. The key advantage of our framework requires only two minimal changes to standard generative processes: (i) variance-boosted initialization and (ii) timestep skipping. We highlight that these seemingly-trivial modifications are supported by solid theoretical and empirical evidence, thereby effectively promoting emergence of underrepresented minority features. Our comprehensive experiments demonstrate that Boost-and-Skip greatly enhances the capability of generating minority samples, even rivaling guidance-based state-of-the-art approaches while requiring significantly fewer computations. Code is available at https://github.com/soobin-um/BnS.
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。