通过频率调控缓解扩散模型的暴露偏差，提升生成质量。
Frequency Regulation for Exposure Bias Mitigation in Diffusion Models
- 利用小波变换动态调节高低频子带，分治处理能量衰减问题。
- 反向过程重构样本能量低于前向过程，且均低于原始数据。
- 无需训练、即插即用，对多种扩散模型有效，开销极小。
扩散模型虽具备出色的生成能力，但严重受制于暴露偏差。本文发现：反向生成过程中预测噪声样本的能量持续低于前向扰动样本。基于此，我们得出两个关键结论：1）能量下降在低频与高频子带中呈现不同模式；2）反向重建样本的子带能量始终低于前向样本，且两者均低于原始数据。据此，我们提出一种基于小波变换的动态频率调节机制，分别调整高低频子带。同时，从第二点推导出暴露偏差的严格数学表达式。所提方法无需训练、可即插即用，显著提升多种扩散模型的生成质量，计算开销可忽略不计。代码已开源：https://github.com/kunzhan/wpp。
原文摘要 · Abstract (English)
Diffusion models exhibit impressive generative capabilities but are significantly impacted by exposure bias. In this paper, we make a key observation: the energy of predicted noisy samples in the reverse process continuously declines compared to perturbed samples in the forward process. Building on this, we identify two important findings: 1) The reduction in energy follows distinct patterns in the low-frequency and high-frequency subbands; 2) The subband energy of reverse-process reconstructed samples is consistently lower than that of forward-process ones, and both are lower than the original data samples. Based on the first finding, we introduce a dynamic frequency regulation mechanism utilizing wavelet transforms, which separately adjusts the low- and high-frequency subbands. Leveraging the second insight, we derive the rigorous mathematical form of exposure bias. It is worth noting that, our method is training-free and plug-and-play, significantly improving the generative quality of various diffusion models and frameworks with negligible computational cost. The source code is available at https://github.com/kunzhan/wpp.
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。