paper-with-me

Papers

Accelerating Diffusion Sampling with Classifier-based Feature Distillation

2022-11-22 · Wujie Sun, Defang Chen, Can Wang, Deshi Ye, Yan Feng, Chun Chen

Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively aligning output images of $N$-step teacher sampler with $N/2$-step student sampler. In this paper, we argue that this distillation-based accelerating method can be further improved, especially for few-step samplers, with our proposed \textbf{C}lassifier-based \textbf{F}eature \textbf{D}istillation (CFD). Instead of aligning output images, we distill teacher's sharpened feature distribution into the student with a dataset-independent classifier, making the student focus on those important features to improve performance. We also introduce a dataset-oriented loss to further optimize the model. Experiments on CIFAR-10 show the superiority of our method in achieving high quality and fast sampling. Code is provided at \url{https://github.com/zju-SWJ/RCFD}.

📄 PDF Abstract BibTeX arXiv:2211.12039

Code (1)

zju-swj/rcfd 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
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…

Similar Papers 제목 키워드 기반

Attention Distillation: A Unified Approach to Visual Characteristics Transfer

2025-02-27 · CVPR 2025 1 · Yang Zhou, Xu Gao, Zichong Chen, Hui Huang

Recent advances in generative diffusion models have shown a notable inherent understanding of image style and semantics. In this paper, we leverage the self-attention features from pretrained diffusion networks to transf…

DenoisingImage Generation

Accelerating Diffusion Models with One-to-Many Knowledge Distillation

2024-10-05 · Linfeng Zhang, Kaisheng Ma

Significant advancements in image generation have been made with diffusion models. Nevertheless, when contrasted with previous generative models, diffusion models face substantial computational overhead, leading to failu…

Image GenerationKnowledge Distillation

On Distillation of Guided Diffusion Models

2022-10-06 · CVPR 2023 1 · Chenlin Meng, Robin Rombach, Ruiqi Gao, Diederik P. Kingma 외

Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Di…

DenoisingImage Generationtext-guided-image-editing

Presto! Distilling Steps and Layers for Accelerating Music Generation

2024-10-07 · Zachary Novack, Ge Zhu, Jonah Casebeer, Julian McAuley 외

Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers …

DiversityMusic Generation

Accelerating the Generation of Molecular Conformations with Progressive Distillation of Equivariant Latent Diffusion Models

2024-04-21 · Romain Lacombe, Neal Vaidya

Recent advances in fast sampling methods for diffusion models have demonstrated significant potential to accelerate generation on image modalities. We apply these methods to 3-dimensional molecular conformations by build…

Drug Discovery