# In Search of Lost Online Test-time Adaptation: A Survey

arXiv: https://arxiv.org/abs/2310.20199 · HTML: https://mlsanity.com/paper/2310.20199/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 99 of its 138 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 30 of 99)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)

## Built on by (most cited first, 30 of 44)

- [Beyond Model Adaptation at Test Time: A Survey](https://mlsanity.com/paper/2411.03687/) (2024)
- [Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach](https://mlsanity.com/paper/2408.07511/) (2024)
- [MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent](https://mlsanity.com/paper/2511.18810/) (2025)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [Improving Black-box Robustness with In-Context Rewriting](https://mlsanity.com/paper/2402.08225/) (2024)
- [A Layer Selection Approach to Test Time Adaptation](https://mlsanity.com/paper/2404.03784/) (2024)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [LoRA-TTT: Low-Rank Test-Time Training for Vision-Language Models](https://mlsanity.com/paper/2502.02069/) (2025)
- [Self-Bootstrapping for Versatile Test-Time Adaptation](https://mlsanity.com/paper/2504.08010/) (2025)
- [SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning](https://mlsanity.com/paper/2503.10252/) (2025)
- [DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection](https://mlsanity.com/paper/2406.13891/) (2024)
- [CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation](https://mlsanity.com/paper/2507.14312/) (2025)
- [Buffer layers for Test-Time Adaptation](https://mlsanity.com/paper/2510.21271/) (2025)
- [A Large Scale Benchmark for Test Time Adaptation Methods in Medical Image Segmentation](https://mlsanity.com/paper/2512.02497/) (2025)
- [FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement](https://mlsanity.com/paper/2607.01111/) (2026)
- [Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation](https://mlsanity.com/paper/2410.14729/) (2024)
- [Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2312.01835/) (2023)
- [Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization](https://mlsanity.com/paper/2509.04977/) (2025)
- [DermoGPT: Open Weights and Open Data for Morphology-Grounded Dermatological Reasoning MLLMs](https://mlsanity.com/paper/2601.01868/) (2026)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [Consistent and Invariant Generalization Learning for Short-video Misinformation Detection](https://mlsanity.com/paper/2507.04061/) (2025)
- [Efficient Test-Time Adaptation through Latent Subspace Coefficients Search](https://mlsanity.com/paper/2510.11068/) (2025)
- [On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective](https://mlsanity.com/paper/2605.28057/) (2026)
- [Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignment](https://mlsanity.com/paper/2405.07171/) (2024)
- [EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems](https://mlsanity.com/paper/2505.00986/) (2025)
- [CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving](https://mlsanity.com/paper/2505.16524/) (2025)
- [Sample-Aware Test-Time Adaptation for Medical Image-to-Image Translation](https://mlsanity.com/paper/2508.00766/) (2025)
- [Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation](https://mlsanity.com/paper/2508.03388/) (2025)
- [HyperTTA: Test-Time Adaptation for Hyperspectral Image Classification under Distribution Shifts](https://mlsanity.com/paper/2509.08436/) (2025)
- [Instance-Aware Test-Time Segmentation for Continual Domain Shifts](https://mlsanity.com/paper/2512.08569/) (2025)

## Abstract (arXiv)

This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of OTTA methods, conclusions from previous studies are inconsistent due to ambiguous settings, outdated backbones, and inconsistent hyperparameter tuning, which obscure core challenges and hinder reproducibility. To enhance clarity and enable rigorous comparison, we classify OTTA techniques into three primary categories and benchmark them using a modern backbone, the Vision Transformer (ViT). Our benchmarks cover conventional corrupted datasets such as CIFAR-10/100-C and ImageNet-C, as well as real-world shifts represented by CIFAR-10.1, OfficeHome, and CIFAR-10-Warehouse. The CIFAR-10-Warehouse dataset includes a variety of variations from different search engines and synthesized data generated through diffusion models. To measure efficiency in online scenarios, we introduce novel evaluation metrics, including GFLOPs, wall clock time, and GPU memory usage, providing a clearer picture of the trade-offs between adaptation accuracy and computational overhead. Our findings diverge from existing literature, revealing that (1) transformers demonstrate heightened resilience to diverse domain shifts, (2) the efficacy of many OTTA methods relies on large batch sizes, and (3) stability in optimization and resistance to perturbations are crucial during adaptation, particularly when the batch size is 1. Based on these insights, we highlight promising directions for future research. Our benchmarking toolkit and source code are available at https://github.com/Jo-wang/OTTA_ViT_survey.