Paper Reading AI Learner

Accelerating Guided Diffusion Sampling with Splitting Numerical Methods

2023-01-27 06:48:29
Suttisak Wizadwongsa, Supasorn Suwajanakorn

Abstract

Guided diffusion is a technique for conditioning the output of a diffusion model at sampling time without retraining the network for each specific task. One drawback of diffusion models, however, is their slow sampling process. Recent techniques can accelerate unguided sampling by applying high-order numerical methods to the sampling process when viewed as differential equations. On the contrary, we discover that the same techniques do not work for guided sampling, and little has been explored about its acceleration. This paper explores the culprit of this problem and provides a solution based on operator splitting methods, motivated by our key finding that classical high-order numerical methods are unsuitable for the conditional function. Our proposed method can re-utilize the high-order methods for guided sampling and can generate images with the same quality as a 250-step DDIM baseline using 32-58% less sampling time on ImageNet256. We also demonstrate usage on a wide variety of conditional generation tasks, such as text-to-image generation, colorization, inpainting, and super-resolution.

Abstract (translated)

Guided diffusion是一种技术,可以在采样时对扩散模型的输出进行条件化,而无需对网络进行每个具体任务的训练。然而,扩散模型的一个缺点是它们的采样过程较慢。最近的技术可以通过将采样过程视为差分方程应用高阶数值方法来加速非引导采样。相反,我们发现,同样的技术对于引导采样并不适用,并且关于它的加速研究较少。本文探讨了这个问题的根源,并基于操作分治方法提出了解决方案,因为我们的关键发现是高阶经典数值方法不适合条件函数。我们提出的这种方法可以再次利用高阶方法用于引导采样,在ImageNet256上生成与250步DDIM基线相同的质量的图像,使用比引导采样少32-58%的采样时间。我们还展示了使用多种条件生成任务的应用,例如文本到图像生成、色彩化、填充和超分辨率。

URL

https://arxiv.org/abs/2301.11558

PDF

https://arxiv.org/pdf/2301.11558.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot