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

arXiv: https://arxiv.org/abs/2207.03442 · HTML: https://mlsanity.com/paper/2207.03442/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 63 references that are in the map.
- First posted on arXiv 7 Jul 2022.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Fast Sampling of Diffusion Models with Exponential Integrator](https://mlsanity.com/paper/2204.13902/) (2022)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)

## Built on by (most cited first, 30 of 71)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Test-Time Learning for Large Language Models](https://mlsanity.com/paper/2505.20633/) (2025)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [TEA: Test-time Energy Adaptation](https://mlsanity.com/paper/2311.14402/) (2023)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging](https://mlsanity.com/paper/2505.11883/) (2025)
- [Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams](https://mlsanity.com/paper/2407.12128/) (2024)
- [Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification](https://mlsanity.com/paper/2306.02544/) (2023)
- [CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation](https://mlsanity.com/paper/2407.16193/) (2024)
- [Test-time Adaptation for Regression by Subspace Alignment](https://mlsanity.com/paper/2410.03263/) (2024)
- [Noisy Test-Time Adaptation in Vision-Language Models](https://mlsanity.com/paper/2502.14604/) (2025)
- [Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptation](https://mlsanity.com/paper/2402.09604/) (2024)
- [GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation](https://mlsanity.com/paper/2410.16606/) (2024)
- [REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation](https://mlsanity.com/paper/2309.03964/) (2023)
- [A Layer Selection Approach to Test Time Adaptation](https://mlsanity.com/paper/2404.03784/) (2024)
- [Test-Time Adaptation in Point Clouds: Leveraging Sampling Variation with Weight Averaging](https://mlsanity.com/paper/2411.01116/) (2024)
- [Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models](https://mlsanity.com/paper/2411.14495/) (2024)
- [AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler](https://mlsanity.com/paper/2407.10784/) (2024)
- [Bi-TTA: Bidirectional Test-Time Adapter for Remote Physiological Measurement](https://mlsanity.com/paper/2409.17316/) (2024)
- [Analytic Continual Test-Time Adaptation for Multi-Modality Corruption](https://mlsanity.com/paper/2410.22373/) (2024)
- [Attention Bootstrapping for Multi-Modal Test-Time Adaptation](https://mlsanity.com/paper/2503.02221/) (2025)
- [Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions](https://mlsanity.com/paper/2510.22127/) (2025)
- [Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation](https://mlsanity.com/paper/2408.13983/) (2024)
- [SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds](https://mlsanity.com/paper/2505.19546/) (2025)
- [Single Image Test-Time Adaptation for Segmentation](https://mlsanity.com/paper/2309.14052/) (2023)
- [Weakly Supervised Test-Time Domain Adaptation for Object Detection](https://mlsanity.com/paper/2407.05607/) (2024)
- [Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation](https://mlsanity.com/paper/2504.12606/) (2025)
- [ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates](https://mlsanity.com/paper/2508.05898/) (2025)
- [Purge-Gate: Backpropagation-Free Test-Time Adaptation for Point Clouds Classification via Token Purging](https://mlsanity.com/paper/2509.09785/) (2025)

## 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.