Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions

• URL: http://arxiv.org/abs/2502.09609v2
• Date: Fri, 14 Feb 2025 02:32:22 GMT
• Title: Score-of-Mixture Training: Training One-Step Generative Models Made Simple via Score Estimation of Mixture Distributions
• Authors: Tejas Jayashankar, J. Jon Ryu, Gregory Wornell,
• Abstract summary: We propose Score-of-Mixture Training (SMT), a novel framework for training one-step generative models. SMT estimates the score of mixture distributions between real and fake samples across multiple noise levels. Our approach supports both training from scratch (SMT) and distillation using a pretrained diffusion model, which we call Score-of-Mixture Distillation (SMD)
• Score: 3.347388046213879
• License:
• Abstract: We propose Score-of-Mixture Training (SMT), a novel framework for training one-step generative models by minimizing a class of divergences called the $\alpha$-skew Jensen-Shannon divergence. At its core, SMT estimates the score of mixture distributions between real and fake samples across multiple noise levels. Similar to consistency models, our approach supports both training from scratch (SMT) and distillation using a pretrained diffusion model, which we call Score-of-Mixture Distillation (SMD). It is simple to implement, requires minimal hyperparameter tuning, and ensures stable training. Experiments on CIFAR-10 and ImageNet 64x64 show that SMT/SMD are competitive with and can even outperform existing methods.

Related papers

• Decouple-Then-Merge: Towards Better Training for Diffusion Models [45.89372687373466]
  Diffusion models are trained by learning a sequence of models that reverse each step of noise corruption. This work proposes a Decouple-then-Merge (DeMe) framework, which begins with a pretrained model and finetunes separate models tailored to specific timesteps.
  arXiv  Detail & Related papers  (2024-10-09T08:19:25Z)
• EM Distillation for One-step Diffusion Models [65.57766773137068]
  We propose a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of quality. We develop a reparametrized sampling scheme and a noise cancellation technique that together stabilizes the distillation process.
  arXiv  Detail & Related papers  (2024-05-27T05:55:22Z)
• Directly Denoising Diffusion Models [6.109141407163027]
  We present Directly Denoising Diffusion Model (DDDM), a simple and generic approach for generating realistic images with few-step sampling. Our model achieves FID scores of 2.57 and 2.33 on CIFAR-10 in one-step and two-step sampling respectively, surpassing those obtained from GANs and distillation-based models. For ImageNet 64x64, our approach stands as a competitive contender against leading models.
  arXiv  Detail & Related papers  (2024-05-22T11:20:32Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training. It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models. While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• One More Step: A Versatile Plug-and-Play Module for Rectifying Diffusion Schedule Flaws and Enhancing Low-Frequency Controls [77.42510898755037]
  One More Step (OMS) is a compact network that incorporates an additional simple yet effective step during inference. OMS elevates image fidelity and harmonizes the dichotomy between training and inference, while preserving original model parameters. Once trained, various pre-trained diffusion models with the same latent domain can share the same OMS module.
  arXiv  Detail & Related papers  (2023-11-27T12:02:42Z)
• Improved Techniques for Training Consistency Models [13.475711217989975]
  We present improved techniques for consistency training, where consistency models learn directly from data without distillation. We propose a lognormal noise schedule for the consistency training objective, and propose to double total discretization steps every set number of training iterations. These modifications enable consistency models to achieve FID scores of 2.51 and 3.25 on CIFAR-10 and ImageNet $64times 64$ respectively in a single sampling step.
  arXiv  Detail & Related papers  (2023-10-22T05:33:38Z)
• A Data Cartography based MixUp for Pre-trained Language Models [47.90235939359225]
  MixUp is a data augmentation strategy where additional samples are generated during training by combining random pairs of training samples and their labels. We propose TDMixUp, a novel MixUp strategy that leverages Training Dynamics and allows more informative samples to be combined for generating new data samples. We empirically validate that our method not only achieves competitive performance using a smaller subset of the training data compared with strong baselines, but also yields lower expected calibration error on the pre-trained language model, BERT, on both in-domain and out-of-domain settings in a wide range of NLP tasks.
  arXiv  Detail & Related papers  (2022-05-06T17:59:19Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Jigsaw Clustering for Unsupervised Visual Representation Learning [68.09280490213399]
  We propose a new jigsaw clustering pretext task in this paper. Our method makes use of information from both intra- and inter-images. It is even comparable to the contrastive learning methods when only half of training batches are used.
  arXiv  Detail & Related papers  (2021-04-01T08:09:26Z)
• Denoising Diffusion Implicit Models [117.03720513930335]
  We present denoising diffusion implicit models (DDIMs) for iterative implicit probabilistic models with the same training procedure as DDPMs. DDIMs can produce high quality samples $10 times$ to $50 times$ faster in terms of wall-clock time compared to DDPMs.
  arXiv  Detail & Related papers  (2020-10-06T06:15:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.