Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions

• URL: http://arxiv.org/abs/2604.23636v1
• Date: Sun, 26 Apr 2026 09:49:18 GMT
• Title: Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions
• Abstract summary: We study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts.<n>We propose a diffusion-based, input-level adaptation framework that operates entirely at test time.<n>We evaluate the proposed approach across a broad spectrum of corruption-induced target domains.
• Score: 10.408270076003769
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this work, we study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts, where performance degradation is caused by natural image corruptions that go beyond additive noise, including blur, weather effects, and digital artifacts. We propose a diffusion-based, input-level adaptation framework that operates entirely at test time and keeps all source-trained models frozen, explicitly targeting robustness to corrupted target inputs. Our method leverages a source-trained diffusion model as a generative prior and introduces a discriminator-guided adaptive diffusion strategy that dynamically controls the amount of perturbation applied to each test sample. Rather than relying on a fixed diffusion depth, the discriminator determines, on a per-image basis, when sufficient forward diffusion has been applied to suppress corruption-specific artifacts, with each corruption type effectively defining a distinct target domain. This adaptive stopping mechanism applies only the necessary amount of noise to remove domainspecific corruption while preserving class-discriminative structure. The reverse diffusion process then reconstructs a source-aligned image, optionally stabilized through structural guidance, which is classified using a frozen source-trained classifier. We evaluate the proposed approach across a broad spectrum of corruption-induced target domains, covering 15 diverse corruption types, and demonstrate more balanced robustness with competitive or improved performance across non-noise corruptions. Additional analyses reveal how the adaptive diffusion schedule responds to different corruption characteristics, highlighting the practicality, generality, and robustness of the proposed framework. The code is publicly available at https://github.com/fmolivato/dgadiffusion/.

Related papers

• PISA: A Pseudo-Individual Source-Domain Feature Adaptation Framework for Test-Time Open-Vocabulary Object Detection [3.403013334650533]
  PISA is a source-free OVOD-TTA method seamlessly integrated into open-vocabulary visual backbones.<n>We show PISA substantially improves both the localization precision and the category recognition accuracy of the original models.
  arXiv  Detail & Related papers  (2026-08-14T09:47:44Z)
• Source-Agnostic Image Translation Based on Latent Aware Adaptive Masking [2.0673681624647844]
  We propose a source-agnostic framework that dynamically refines a binary mask throughout the reverse diffusion process.<n>Our method introduces a time-dependent statistical thresholding scheme derived from the empirical mean and standard deviation of prediction discrepancies.<n>Our approach enables precise, automated localization and seamless translation across diverse source distributions without any specialized training.
  arXiv  Detail & Related papers  (2026-08-14T07:51:40Z)
• Simplex Relaxation for Discrete Diffusion [58.33696160279345]
  We introduce Simplax, an exact Dirichlet--categorical augmentation that couples each corrupted categorical state with an auxiliary simplex-valued variable.<n>Simplax improves the generative perplexity--entropy tradeoff on unconditional OpenWebText generation.
  arXiv  Detail & Related papers  (2026-08-11T07:58:17Z)
• Inference-Time Attribute Distribution Alignment for Unconditional Diffusion [54.28942858023809]
  We formalize the inference-time attribute distributional alignment problem for pretrained unconditional diffusion models.<n>To address this, we cast inference-time attribute distributional alignment as an optimal control problem over the reverse diffusion process.<n>We solve for the perturbations using an optimal-control-based algorithm to optimize a differentiable distribution-matching objective.
  arXiv  Detail & Related papers  (2026-05-08T09:02:47Z)
• Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation [11.673350359272716]
  Discriminative Vicinity Diffusion (DVD) is a framework for a practical variant of source-free domain adaptation.<n>DVD encodes each source feature's label information into its latent vicinity.<n>We show that DVD outperforms state-of-the-art methods across standard SFDA benchmarks.
  arXiv  Detail & Related papers  (2025-10-01T03:58:26Z)
• What is Adversarial Training for Diffusion Models? [4.71482540145286]
  We show that adversarial training (AT) for diffusion models (DMs) fundamentally differs from classifiers.<n>AT is a way to enforce smoothness in the diffusion flow, improving to outliers and corrupted data.<n>We rigorously evaluate our approach with proof-of-concept datasets with known distributions in low- and high-dimensional space.
  arXiv  Detail & Related papers  (2025-05-27T20:32:28Z)
• DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks [79.50756148780928]
  This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks.<n>We extend the discriminative capability of pretrained frozen generative diffusion models from the classification task to the more complex object detection task, by "inverting" a pretrained layout-to-image diffusion model.
  arXiv  Detail & Related papers  (2025-04-24T05:13:27Z)
• Diffusion Model Driven Test-Time Image Adaptation for Robust Skin Lesion Classification [24.08402880603475]
  We propose a test-time image adaptation method to enhance the accuracy of the model on test data. We modify the target test images by projecting them back to the source domain using a diffusion model. Our method makes the robustness more robust across various corruptions, architectures, and data regimes.
  arXiv  Detail & Related papers  (2024-05-18T13:28:51Z)
• Generative Model Based Noise Robust Training for Unsupervised Domain Adaptation [108.11783463263328]
  This paper proposes a Generative model-based Noise-Robust Training method (GeNRT) It eliminates domain shift while mitigating label noise. Experiments on Office-Home, PACS, and Digit-Five show that our GeNRT achieves comparable performance to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-03-10T06:43:55Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Soft Diffusion: Score Matching for General Corruptions [84.26037497404195]
  We propose a new objective called Soft Score Matching that provably learns the score function for any linear corruption process. We show that our objective learns the gradient of the likelihood under suitable regularity conditions for the family of corruption processes. Our method achieves state-of-the-art FID score $1.85$ on CelebA-64, outperforming all previous linear diffusion models.
  arXiv  Detail & Related papers  (2022-09-12T17:45:03Z)
• Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks [86.42889611784855]
  normalization methods increase the vulnerability with respect to noise and input corruptions. We propose an unsupervised non-parametric distribution correction method that adapts the activation distribution of each layer. In our experiments, we empirically show that the proposed method effectively reduces the impact of intense image corruptions.
  arXiv  Detail & Related papers  (2021-10-05T11:36:25Z)
• Contradictory Structure Learning for Semi-supervised Domain Adaptation [67.89665267469053]
  Current adversarial adaptation methods attempt to align the cross-domain features. Two challenges remain unsolved: 1) the conditional distribution mismatch and 2) the bias of the decision boundary towards the source domain. We propose a novel framework for semi-supervised domain adaptation by unifying the learning of opposite structures.
  arXiv  Detail & Related papers  (2020-02-06T22:58:20Z)

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.