paper-with-me

Papers

DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach

2024-10-12 · Daniel Gallo Fernández, Răzvan-Andrei Matişan, Alejandro Monroy Muñoz, Ana-Maria Vasilcoiu, Janusz Partyka, Tin Hadži Veljković, Metod Jazbec

Diffusion models have achieved unprecedented performance in image generation, yet they suffer from slow inference due to their iterative sampling process. To address this, early-exiting has recently been proposed, where the depth of the denoising network is made adaptive based on the (estimated) difficulty of each sampling step. Here, we discover an interesting "phase transition" in the sampling process of current adaptive diffusion models: the denoising network consistently exits early during the initial sampling steps, until it suddenly switches to utilizing the full network. Based on this, we propose accelerating generation by employing a shallower denoising network in the initial sampling steps and a deeper network in the later steps. We demonstrate empirically that our dual-backbone approach, DuoDiff, outperforms existing early-exit diffusion methods in both inference speed and generation quality. Importantly, DuoDiff is easy to implement and complementary to existing approaches for accelerating diffusion.

📄 PDF Abstract BibTeX arXiv:2410.09633

Code (1)

razvanmatisan/duodiff 공식 구현 pytorch

Tasks

DenoisingImage Generation

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

MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shifting

2025-03-03 · Mojtaba Safari, Shansong Wang, Zach Eidex, Qiang Li 외

Objective:This study introduces a residual error-shifting mechanism that drastically reduces sampling steps while preserving critical anatomical details, thus accelerating MRI reconstruction. Approach:We propose a novel …

Computational EfficiencyDenoisingImage ReconstructionImage Restoration+3

Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment

2025-05-26 · Jeongsoo Choi, Zhikang Niu, Ji-Hoon Kim, Chunhui Wang 외

The goal of this paper is to optimize the training process of diffusion-based text-to-speech models. While recent studies have achieved remarkable advancements, their training demands substantial time and computational c…

text-to-speechText to Speech

Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

2024-06-04 · Clément Chadebec, Onur Tasar, Eyal Benaroche, Benjamin Aubin

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of …

Face SwappingGPUImage GenerationImage Inpainting+1

Prior-Guided Residual Diffusion: Calibrated and Efficient Medical Image Segmentation

2025-09-01 · Fuyou Mao, Beining Wu, Yanfeng Jiang, Han Xue 외 arxiv

Ambiguity in medical image segmentation calls for models that capture full conditional distributions rather than a single point estimate. We present Prior-Guided Residual Diffusion (PGRD), a diffusion-based framework tha…

Medical Image Segmentation

Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network

2026-05-18 · Grigory Bartosh, David Ruhe, Emiel Hoogeboom, Jonathan Heek 외 arxiv

Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network. In this work, we propose Dual-Rate Diff…