paper-with-me

Papers

Optimizing DDPM Sampling with Shortcut Fine-Tuning

2023-01-31 · Ying Fan, Kangwook Lee

In this study, we propose Shortcut Fine-Tuning (SFT), a new approach for addressing the challenge of fast sampling of pretrained Denoising Diffusion Probabilistic Models (DDPMs). SFT advocates for the fine-tuning of DDPM samplers through the direct minimization of Integral Probability Metrics (IPM), instead of learning the backward diffusion process. This enables samplers to discover an alternative and more efficient sampling shortcut, deviating from the backward diffusion process. Inspired by a control perspective, we propose a new algorithm SFT-PG: Shortcut Fine-Tuning with Policy Gradient, and prove that under certain assumptions, gradient descent of diffusion models with respect to IPM is equivalent to performing policy gradient. To our best knowledge, this is the first attempt to utilize reinforcement learning (RL) methods to train diffusion models. Through empirical evaluation, we demonstrate that our fine-tuning method can further enhance existing fast DDPM samplers, resulting in sample quality comparable to or even surpassing that of the full-step model across various datasets.

📄 PDF Abstract BibTeX arXiv:2301.13362

Code (1)

uw-madison-lee-lab/sft-pg 공식 구현 pytorch

Tasks

DenoisingReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…

Similar Papers 제목 키워드 기반

Optimizing Few-Step Diffusion Samplers by Gradient Descent

2021-09-29 · ICLR 2022 4 · Daniel Watson, William Chan, Jonathan Ho, Mohammad Norouzi

Denoising Diffusion Probabilistic Models (DDPMs) have emerged as a flexible family of generative models rivaling GANs and autoregressive models in sample quality and likelihoods. DDPMs however typically require hundreds …

DenoisingImage GenerationUnconditional Image Generation

You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts

2025-05-12 · Hongkun Dou, Zeyu Li, Xingyu Jiang, Hongjue Li 외

Diffusion models (DMs) have recently demonstrated remarkable success in modeling large-scale data distributions. However, many downstream tasks require guiding the generated content based on specific differentiable metri…

Denoising

Bilateral Denoising Diffusion Models

2021-08-26 · Max W. Y. Lam, Jun Wang, Rongjie Huang, Dan Su 외

Denoising diffusion probabilistic models (DDPMs) have emerged as competitive generative models yet brought challenges to efficient sampling. In this paper, we propose novel bilateral denoising diffusion models (BDDMs), w…

DenoisingScheduling

Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks

2025-07-24 · Binghua Li, Ziqing Chang, Tong Liang, Chao Li 외 arxiv

We address the challenge of parameter-efficient fine-tuning (PEFT) for three-dimensional (3D) U-Net-based denoising diffusion probabilistic models (DDPMs) in magnetic resonance imaging (MRI) image generation. Despite its…

parameter-efficient fine-tuningImage Generation

Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling

2024-07-08 · Lintao Zhang, Xiangcheng Du, LeoWu TomyEnrique, Yiqun Wang 외

For image inpainting, the existing Denoising Diffusion Probabilistic Model (DDPM) based method i.e. RePaint can produce high-quality images for any inpainting form. It utilizes a pre-trained DDPM as a prior and generates…

DenoisingImage Inpainting