Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Models

• URL: http://arxiv.org/abs/2505.11482v3
• Date: Mon, 26 May 2025 15:24:04 GMT
• Title: Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Models
• Authors: Shirin Shoushtari, Edward P. Chandler, Yuanhao Wang, M. Salman Asif, Ulugbek S. Kamilov,
• Abstract summary: We propose a fully unsupervised metric for estimating distribution shifts using only indirect (corrupted) measurements.<n>We show that our score-based metric, using only corrupted measurements, closely approximates the KL divergence computed from clean images.<n>Motivated by this result, we show that aligning the out-of-distribution score with the in-distribution score -- using only corrupted measurements -- reduces the KL divergence and leads to improved reconstruction quality across multiple inverse problems.
• Score: 15.926651846862544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models are widely used as priors in imaging inverse problems. However, their performance often degrades under distribution shifts between the training and test-time images. Existing methods for identifying and quantifying distribution shifts typically require access to clean test images, which are almost never available while solving inverse problems (at test time). We propose a fully unsupervised metric for estimating distribution shifts using only indirect (corrupted) measurements and score functions from diffusion models trained on different datasets. We theoretically show that this metric estimates the KL divergence between the training and test image distributions. Empirically, we show that our score-based metric, using only corrupted measurements, closely approximates the KL divergence computed from clean images. Motivated by this result, we show that aligning the out-of-distribution score with the in-distribution score -- using only corrupted measurements -- reduces the KL divergence and leads to improved reconstruction quality across multiple inverse problems.

Related papers

• Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching [35.01013208265617]
  This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets.<n>The proposed method operates under minimal assumptions and relies only on small, unpaired datasets.<n>It is particularly well-suited for real-world scenarios, where the forward model is often unknown or misspecified.
  arXiv  Detail & Related papers  (2025-06-17T15:06:43Z)
• EquiReg: Equivariance Regularized Diffusion for Inverse Problems [67.01847869495558]
  We propose EquiReg diffusion, a framework for regularizing posterior sampling in diffusion-based inverse problem solvers.<n>When applied to a variety of solvers, EquiReg outperforms state-of-the-art diffusion models in both linear and nonlinear image restoration tasks.
  arXiv  Detail & Related papers  (2025-05-29T01:25:43Z)
• Measurement Score-Based Diffusion Model [5.82978411250693]
  Measurement Score-based diffusion Model (MSM) is a novel framework that learns partial measurement scores using only noisy and subsampled measurements.<n>MSM can generate high-quality images and solve inverse problems -- all without access to clean training data.
  arXiv  Detail & Related papers  (2025-05-17T05:33:47Z)
• Traversing Distortion-Perception Tradeoff using a Single Score-Based Generative Model [35.91741991271154]
  distortion-perception tradeoff reveals a fundamental conflict between distortion metrics and perceptual quality.<n>We show that a single score network can effectively and flexibly traverse the DP tradeoff for general denoising problems.
  arXiv  Detail & Related papers  (2025-03-26T07:37:53Z)
• Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models [22.39558434131574]
  Existing data attribution methods for diffusion models typically quantify the contribution of a training sample.<n>We argue that the direct usage of diffusion loss cannot represent such a contribution accurately due to the calculation of diffusion loss.<n>We propose Diffusion Attribution Score (textitDAS) to measure the direct comparison between predicted distributions with an attribution score.
  arXiv  Detail & Related papers  (2024-10-24T10:58:17Z)
• Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problems [12.5216516851131]
  We study out of distribution (OOD) problems where a known training distribution is first provided. We use a patch-based diffusion prior that learns the image distribution solely from patches. In both settings, the patch-based method can obtain high quality image reconstructions that can outperform whole-image models.
  arXiv  Detail & Related papers  (2024-10-15T16:02:08Z)
• Think Twice Before You Act: Improving Inverse Problem Solving With MCMC [40.5682961122897]
  We propose textbfDiffusion textbfPosterior textbfMCMC (textbfDPMC) to solve inverse problems with pretrained diffusion models. Our algorithm outperforms DPS with less number of evaluations across nearly all tasks, and is competitive among existing approaches.
  arXiv  Detail & Related papers  (2024-09-13T06:10:54Z)
• Amortized Posterior Sampling with Diffusion Prior Distillation [55.03585818289934]
  Amortized Posterior Sampling is a novel variational inference approach for efficient posterior sampling in inverse problems.<n>Our method trains a conditional flow model to minimize the divergence between the variational distribution and the posterior distribution implicitly defined by the diffusion model.<n>Unlike existing methods, our approach is unsupervised, requires no paired training data, and is applicable to both Euclidean and non-Euclidean domains.
  arXiv  Detail & Related papers  (2024-07-25T09:53:12Z)
• Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models [72.07462371883501]
  We propose emphProjection Regret (PR), an efficient novelty detection method that mitigates the bias of non-semantic information. PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.
  arXiv  Detail & Related papers  (2023-12-05T09:44:47Z)
• A Variational Perspective on Solving Inverse Problems with Diffusion Models [101.831766524264]
  Inverse tasks can be formulated as inferring a posterior distribution over data. This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable. We propose a variational approach that by design seeks to approximate the true posterior distribution.
  arXiv  Detail & Related papers  (2023-05-07T23:00:47Z)
• 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)
• Denoising Diffusion Restoration Models [110.1244240726802]
  Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method. We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
  arXiv  Detail & Related papers  (2022-01-27T20:19:07Z)

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.