paper-with-me

Papers

SFDDM: Single-fold Distillation for Diffusion models

2024-05-23 · Chi Hong, Jiyue Huang, Robert Birke, Dick Epema, Stefanie Roos, Lydia Y. Chen

While diffusion models effectively generate remarkable synthetic images, a key limitation is the inference inefficiency, requiring numerous sampling steps. To accelerate inference and maintain high-quality synthesis, teacher-student distillation is applied to compress the diffusion models in a progressive and binary manner by retraining, e.g., reducing the 1024-step model to a 128-step model in 3 folds. In this paper, we propose a single-fold distillation algorithm, SFDDM, which can flexibly compress the teacher diffusion model into a student model of any desired step, based on reparameterization of the intermediate inputs from the teacher model. To train the student diffusion, we minimize not only the output distance but also the distribution of the hidden variables between the teacher and student model. Extensive experiments on four datasets demonstrate that our student model trained by the proposed SFDDM is able to sample high-quality data with steps reduced to as little as approximately 1%, thus, trading off inference time. Our remarkable performance highlights that SFDDM effectively transfers knowledge in single-fold distillation, achieving semantic consistency and meaningful image interpolation.

📄 PDF Abstract BibTeX arXiv:2405.14961

Code (0)

등록된 구현이 없습니다.

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…

Similar Papers 제목 키워드 기반

ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation

2026-02-26 · Ayush Roy, Wei-Yang Alex Lee, Rudrasis Chakraborty, Vishnu Suresh Lokhande arxiv

In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datasets that preserve the knowledge of large-scale training sets …

Amortized Posterior Sampling with Diffusion Prior Distillation

2024-07-25 · Abbas Mammadov, Hyungjin Chung, Jong Chul Ye

We propose a variational inference approach to sample from the posterior distribution for solving inverse problems. From a pre-trained diffusion model, our approach trains a conditional flow model to minimize the diverge…

Variational Inference

Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning

2025-11-19 · Yuxuan Gu, Weimin Bai, Yifei Wang, Weijian Luo 외 arxiv

Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vanilla MAR suffers from slow inference due …

Reinforcement Learning

Inference-Time Diffusion Model Distillation

2024-12-12 · Geon Yeong Park, Sang Wan Lee, Jong Chul Ye

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model count…

Denoisingmodel

Variance Reduction on the Camera Axis: Multi-View Score Distillation for 3D

2026-06-29 · Marian Lupascu, Mihai Sorin Stupariu, Ionut Mironica arxiv

Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view: it is high-variance and blind to global shape consistency. Prior wo…