Debiasing Kernel-Based Generative Models
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 18 of its 29 references that are in the map. First posted on arXiv 26 Mar 2025.
Builds on
18 of 29 references.
Closest ancestors · 2
Same direction, newest first
- 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
- 2020Denoising Diffusion Probabilistic Models19 Jun
Other references · 16
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
- 2022Video Diffusion Modelscited by 2,305
- 2015Variational Inference with Normalizing Flowscited by 2,170
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
- 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 384
- 2017Wasserstein Auto-Encoderscited by 373
4 more
- 2015Stochastic modified equations and adaptive stochastic gradient algorithmscited by 142
- 2016Video Pixel Networkscited by 108
- 2018Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscalingcited by 74
- 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Balancing Act: Distribution-Guided Debiasing in Diffusion Models
- 2024DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection
- 2025DeblurDiff: Real-World Image Deblurring with Generative Diffusion Models
- 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
- 2025Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study
- 2025Inference Time Debiasing Concepts in Diffusion Models
- 2025Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation
- 2022Convergence of score-based generative modeling for general data distributions