优化去噪得分匹配会引入得分范数偏高问题，影响多类生成模型性能。
Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm
- 通过分析发现，输入优化破坏了去噪与精确得分匹配的等价性
- 该方法导致得分范数显著升高，存在系统性偏差
- 影响文本到3D生成、图像压缩等多个前沿领域
近期多项研究利用去噪得分匹配来优化扩散模型的条件输入。本文指出，此类优化破坏了去噪得分匹配与精确得分匹配之间的等价性，并导致得分范数升高。此外，当使用预训练扩散模型优化数据分布时也观察到类似偏差。该偏差广泛影响多个领域的工作，包括自回归生成中的MAR、图像压缩中的PerCo，以及文本到3D生成中的DreamFusion。
原文摘要 · Abstract (English)
Many recent works utilize denoising score matching to optimize the conditional input of diffusion models. In this workshop paper, we demonstrate that such optimization breaks the equivalence between denoising score matching and exact score matching. Furthermore, we show that this bias leads to higher score norm. Additionally, we observe a similar bias when optimizing the data distribution using a pre-trained diffusion model. Finally, we discuss the wide range of works across different domains that are affected by this bias, including MAR for auto-regressive generation, PerCo for image compression, and DreamFusion for text to 3D generation.
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。