Elucidating the Exposure Bias in Diffusion Models

• URL: http://arxiv.org/abs/2308.15321v6
• Date: Wed, 10 Apr 2024 18:13:00 GMT
• Title: Elucidating the Exposure Bias in Diffusion Models
• Authors: Mang Ning, Mingxiao Li, Jianlin Su, Albert Ali Salah, Itir Onal Ertugrul,
• Abstract summary: We investigate the input mismatch between training and sampling in diffusion models. We propose a training-free method called Epsilon Scaling to alleviate the exposure bias. We show that Epsilon Scaling explicitly moves the sampling trajectory closer to the vector field learned in the training phase.
• Score: 7.529885833916501
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion models have demonstrated impressive generative capabilities, but their \textit{exposure bias} problem, described as the input mismatch between training and sampling, lacks in-depth exploration. In this paper, we systematically investigate the exposure bias problem in diffusion models by first analytically modelling the sampling distribution, based on which we then attribute the prediction error at each sampling step as the root cause of the exposure bias issue. Furthermore, we discuss potential solutions to this issue and propose an intuitive metric for it. Along with the elucidation of exposure bias, we propose a simple, yet effective, training-free method called Epsilon Scaling to alleviate the exposure bias. We show that Epsilon Scaling explicitly moves the sampling trajectory closer to the vector field learned in the training phase by scaling down the network output, mitigating the input mismatch between training and sampling. Experiments on various diffusion frameworks (ADM, DDIM, EDM, LDM, DiT, PFGM++) verify the effectiveness of our method. Remarkably, our ADM-ES, as a state-of-the-art stochastic sampler, obtains 2.17 FID on CIFAR-10 under 100-step unconditional generation. The code is available at \url{https://github.com/forever208/ADM-ES} and \url{https://github.com/forever208/EDM-ES}.

Related papers

• A Mixture-Based Framework for Guiding Diffusion Models [19.83064246586143]
  Denoising diffusion models have driven significant progress in the field of Bayesian inverse problems. Recent approaches use pre-trained diffusion models as priors to solve a wide range of such problems. This work proposes a novel mixture approximation of these intermediate distributions.
  arXiv  Detail & Related papers  (2025-02-05T16:26:06Z)
• Amortizing intractable inference in diffusion models for vision, language, and control [89.65631572949702]
  This paper studies amortized sampling of the posterior over data, $mathbfxsim prm post(mathbfx)propto p(mathbfx)r(mathbfx)$, in a model that consists of a diffusion generative model prior $p(mathbfx)$ and a black-box constraint or function $r(mathbfx)$. We prove the correctness of a data-free learning objective, relative trajectory balance, for training a diffusion model that samples from
  arXiv  Detail & Related papers  (2024-05-31T16:18:46Z)
• Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data [74.2507346810066]
  Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. We present the first framework for training diffusion models that provably sample from the uncorrupted distribution given only noisy training data.
  arXiv  Detail & Related papers  (2024-03-20T14:22:12Z)
• Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data [56.81246107125692]
  Ambient Diffusion Posterior Sampling (A-DPS) is a generative model pre-trained on one type of corruption. We show that A-DPS can sometimes outperform models trained on clean data for several image restoration tasks in both speed and performance. We extend the Ambient Diffusion framework to train MRI models with access only to Fourier subsampled multi-coil MRI measurements.
  arXiv  Detail & Related papers  (2024-03-13T17:28:20Z)
• Unmasking Bias in Diffusion Model Training [40.90066994983719]
  Denoising diffusion models have emerged as a dominant approach for image generation. They still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be largely attributed to bias and suboptimality inherent in the default training paradigm.
  arXiv  Detail & Related papers  (2023-10-12T16:04:41Z)
• Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
  Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. We introduce a novel approach that tackles the problem by matching implicit and explicit factors. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
  arXiv  Detail & Related papers  (2023-06-21T18:49:22Z)
• Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision [76.32860119056964]
  We propose a novel class of denoising diffusion probabilistic models that learn to sample from distributions of signals that are never directly observed. We demonstrate the effectiveness of our method on three challenging computer vision tasks.
  arXiv  Detail & Related papers  (2023-06-20T17:53:00Z)
• Interpreting and Improving Diffusion Models from an Optimization Perspective [4.5993996573872185]
  We use this observation to interpret denoising diffusion models as approximate gradient descent applied to the Euclidean distance function. We propose a new gradient-estimation sampler, generalizing DDIM using insights from our theoretical results.
  arXiv  Detail & Related papers  (2023-06-08T00:56:33Z)
• Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps [23.144083737873263]
  Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images. Previous work has attempted to mitigate this issue by perturbing inputs during training. We propose a novel sampling method that we propose, without retraining the model.
  arXiv  Detail & Related papers  (2023-05-24T21:39:27Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent [97.64313409741614]
  We propose to enforce a emphconsistency property which states that predictions of the model on its own generated data are consistent across time. We show that our novel training objective yields state-of-the-art results for conditional and unconditional generation in CIFAR-10 and baseline improvements in AFHQ and FFHQ.
  arXiv  Detail & Related papers  (2023-02-17T18:45:04Z)
• Stable Target Field for Reduced Variance Score Estimation in Diffusion Models [5.9115407007859755]
  Diffusion models generate samples by reversing a fixed forward diffusion process. We argue that the source of such variance lies in the handling of intermediate noise-variance scales. We propose to remedy the problem by incorporating a reference batch which we use to calculate weighted conditional scores as more stable training targets.
  arXiv  Detail & Related papers  (2023-02-01T18:57:01Z)

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.