用核密度估计与去偏算法提升生成模型图像质量
Debiasing Kernel-Based Generative Models
- 先用核密度估计生成图像，再通过迭代去偏算法降模糊
- 在CIFAR10上图像质量媲美扩散模型和GAN
- 适合关注生成模型清晰度与理论机制的研究者
我们提出一种基于核密度估计（KDE）与随机逼近思想的两阶段生成模型框架——去偏核生成模型（DKGM）。第一阶段利用KDE生成图像，避免数据密度估计困难且保持较高图像质量；但KDE固有的过平滑问题导致图像模糊。第二阶段将去模糊过程建模为统计去偏问题，设计新型迭代算法进行优化。大量实验表明，DKGM在CIFAR10上的图像质量达到当前顶尖水平，与扩散模型和GAN相当；在CelebA 128x128与LSUN（Church）128x128上表现也具竞争力。额外实验分析了KDE带宽对样本多样性和去偏效果的影响，并探讨了DKGM与得分函数模型之间的联系。
原文摘要 · Abstract (English)
We propose a novel two-stage framework of generative models named Debiasing Kernel-Based Generative Models (DKGM) with the insights from kernel density estimation (KDE) and stochastic approximation. In the first stage of DKGM, we employ KDE to bypass the obstacles in estimating the density of data without losing too much image quality. One characteristic of KDE is oversmoothing, which makes the generated image blurry. Therefore, in the second stage, we formulate the process of reducing the blurriness of images as a statistical debiasing problem and develop a novel iterative algorithm to improve image quality, which is inspired by the stochastic approximation. Extensive experiments illustrate that the image quality of DKGM on CIFAR10 is comparable to state-of-the-art models such as diffusion models and GAN models. The performance of DKGM on CelebA 128x128 and LSUN (Church) 128x128 is also competitive. We conduct extra experiments to exploit how the bandwidth in KDE affects the sample diversity and debiasing effect of DKGM. The connections between DKGM and score-based models are also discussed.
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。