mlsanityData to 7 Oct 2026

Back to the Source: Diffusion-Driven Test-Time Adaptation

arXiv 2207.03442 ↗First posted 7 Jul 2022cs.LG cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data. Existing methods update the source model by (re-)training on each target domain. While effective, re-training is sensitive to the amount and order of the data and the hyperparameters for optimization. We instead update the target data, by projecting all test inputs toward the source domain with a generative diffusion model. Our diffusion-driven adaptation method, DDA, shares its models for classification and generation across all domains. Both models are trained on the source domain, then fixed during testing. We augment diffusion with image guidance and self-ensembling to automatically decide how much to adapt. Input adaptation by DDA is more robust than prior model adaptation approaches across a variety of corruptions, architectures, and data regimes on the ImageNet-C benchmark. With its input-wise updates, DDA succeeds where model adaptation degrades on too little data in small batches, dependent data in non-uniform order, or mixed data with multiple corruptions.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). Builds on 46 of its 63 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

46 of 63 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  9. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  10. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
34 more
  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  2. 2022A ConvNet for the 2020scited by 3,545
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  9. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  10. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  11. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  12. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  13. 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
  14. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  15. 2022Fast Sampling of Diffusion Models with Exponential Integratorcited by 526
  16. 2022Diffusion Models for Adversarial Purificationcited by 469
  17. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  18. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  19. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  20. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  21. 2020Universal Source-Free Domain Adaptationcited by 219
  22. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211
  23. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  24. 2019Photorealistic Style Transfer via Wavelet Transformscited by 166
  25. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  26. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  27. 2021On Interaction Between Augmentations and Corruptions in Natural Corruption Robustnesscited by 98
  28. 2021Enhancing Photorealism Enhancementcited by 74
  29. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  30. 2020TSIT: A Simple and Versatile Framework for Image-to-Image Translationcited by 64
  31. 2019Test-Time Training with Self-Supervision for Generalization under Distribution Shiftscited by 55
  32. 2021Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restorationcited by 50
  33. 2020Test-time Unsupervised Domain Adaptationcited by 37
  34. 2021Domain Generalization via Inference-time Label-Preserving Target Projectionscited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 22; 2025: 23; 2026: 18.

71 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2025Test-Time Learning for Large Language Modelscited by 46
  3. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 43
  4. 2023TEA: Test-time Energy Adaptationcited by 25
  5. 2025Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Modelscited by 23
  6. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 20
  7. 2025MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Mergingcited by 14
  8. 2024Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streamscited by 13
  9. 2023Fourier Test-time Adaptation with Multi-level Consistency for Robust Classificationcited by 12
  10. 2024CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformationcited by 11
  11. 2024Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptationcited by 9
  12. 2024Test-time Adaptation for Regression by Subspace Alignmentcited by 9
38 more
  1. 2024GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptationcited by 8
  2. 2025Noisy Test-Time Adaptation in Vision-Language Modelscited by 8
  3. 2023REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptationcited by 7
  4. 2024A Layer Selection Approach to Test Time Adaptationcited by 7
  5. 2024Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averagingcited by 7
  6. 2024Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Modelscited by 7
  7. 2024AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handlercited by 6
  8. 2024Bi-TTA: Bidirectional Test-Time Adapter for Remote Physiological Measurementcited by 6
  9. 2024Analytic Continual Test-Time Adaptation for Multi-Modality Corruptioncited by 5
  10. 2025Attention Bootstrapping for Multi-Modal Test-Time Adaptationcited by 5
  11. 2025Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptionscited by 5
  12. 2024Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptationcited by 4
  13. 2025SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Cloudscited by 4
  14. 2023Single Image Test-Time Adaptation for Segmentationcited by 3
  15. 2025Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generationcited by 3
  16. 2025ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updatescited by 3
  17. 2025Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purgingcited by 3
  18. 2024FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distributioncited by 2
  19. 2024Multi-Stream Cellular Test-Time Adaptation of Real-Time Models Evolving in Dynamic Environmentscited by 2
  20. 2024Weakly Supervised Test-Time Domain Adaptation for Object Detectioncited by 2
  21. 2024Towards Unsupervised Blind Face Restoration using Diffusion Priorcited by 2
  22. 2025Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptationcited by 2
  23. 2025Can Diffusion Models Bridge the Domain Gap in Cardiac MR Imaging?cited by 2
  24. 2025FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classificationcited by 2
  25. 2026Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Modelscited by 2
  26. 2026Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridgingcited by 2
  27. 2024MITA: Bridging the Gap between Model and Data for Test-time Adaptationcited by 1
  28. 2024Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Costcited by 1
  29. 2025Beyond Batch Learning: Global Awareness Enhanced Domain Adaptationcited by 1
  30. 2025Defending Against Frequency-Based Attacks with Diffusion Modelscited by 1
  31. 2025Noise Optimized Conditional Diffusion for Domain Adaptationcited by 1
  32. 20253D Test-time Adaptation via Graph Spectral Driven Point Shiftcited by 1
  33. 2026Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrievalcited by 1
  34. 2026Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptationcited by 1
  35. 2026Exploiting Intermediate Reconstructions in Optical Coherence Tomography for Test-Time Adaption of Medical Image Segmentationcited by 1
  36. 2026Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directionscited by 1
  37. 2026Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodalitycited by 1
  38. 2023Two Simple Principles for Diffusion-Based Test-Time Adaptationcited by 0

50 most cited of 71 All 71 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Turn Down the Noise: Leveraging Diffusion Models for Test-time Adaptation via Pseudo-label Ensembling
  2. 2023Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
  3. 2024GDA: Generalized Diffusion for Robust Test-time Adaptation
  4. 2024Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
  5. 2025ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains
  6. 2024Diffusion Model Driven Test-Time Image Adaptation for Robust Skin Lesion Classification
  7. 2025Test-Time Modification: Inverse Domain Transformation for Robust Perception
  8. 2023DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning