# Test time Adaptation through Perturbation Robustness

arXiv: https://arxiv.org/abs/2110.10232 · HTML: https://mlsanity.com/paper/2110.10232/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 19 Oct 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [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)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (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)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Entropy-SGD: Biasing Gradient Descent Into Wide Valleys](https://mlsanity.com/paper/1611.01838/) (2016)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Sensitivity and Generalization in Neural Networks: an Empirical Study](https://mlsanity.com/paper/1802.08760/) (2018)
- [Large Margin Deep Networks for Classification](https://mlsanity.com/paper/1803.05598/) (2018)
- [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://mlsanity.com/paper/1709.01643/) (2017)
- [Unsupervised Domain Adaptation in Semantic Segmentation: a Review](https://mlsanity.com/paper/2005.10876/) (2020)
- [Measuring the tendency of CNNs to Learn Surface Statistical Regularities](https://mlsanity.com/paper/1711.11561/) (2017)
- [Understanding Generalization through Visualizations](https://mlsanity.com/paper/1906.03291/) (2019)
- [Adversarial Feature Augmentation for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1711.08561/) (2017)
- [Robustness via Cross-Domain Ensembles](https://mlsanity.com/paper/2103.10919/) (2021)

## Built on by (most cited first, 28 of 28)

- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [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)
- [DomainAdaptor: A Novel Approach to Test-time Adaptation](https://mlsanity.com/paper/2308.10297/) (2023)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2203.14222/) (2022)
- [Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?](https://mlsanity.com/paper/2302.12480/) (2023)
- [Noisy Test-Time Adaptation in Vision-Language Models](https://mlsanity.com/paper/2502.14604/) (2025)
- [Test-Time Model Adaptation for Quantized Neural Networks](https://mlsanity.com/paper/2508.02180/) (2025)
- [Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation](https://mlsanity.com/paper/2210.10019/) (2022)
- [REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation](https://mlsanity.com/paper/2309.03964/) (2023)
- [Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation](https://mlsanity.com/paper/2405.20596/) (2024)
- [LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2408.05769/) (2024)
- [Single Image Test-Time Adaptation via Multi-View Co-Training](https://mlsanity.com/paper/2506.23705/) (2025)
- [Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentation](https://mlsanity.com/paper/2307.00676/) (2023)
- [Enhancing Plasticity for First Session Adaptation Continual Learning](https://mlsanity.com/paper/2310.11482/) (2023)
- [Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers](https://mlsanity.com/paper/2311.07538/) (2023)
- [Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching](https://mlsanity.com/paper/2403.17423/) (2024)
- [Fully Test-Time Adaptation for Monocular 3D Object Detection](https://mlsanity.com/paper/2405.19682/) (2024)
- [SEVA: Leveraging Single-Step Ensemble of Vicinal Augmentations for Test-Time Adaptation](https://mlsanity.com/paper/2505.04087/) (2025)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization](https://mlsanity.com/paper/2603.14254/) (2026)
- [Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignment](https://mlsanity.com/paper/2405.07171/) (2024)
- [Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving](https://mlsanity.com/paper/2411.18860/) (2024)
- [Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes](https://mlsanity.com/paper/2506.10653/) (2025)

## Abstract (arXiv)

Data samples generated by several real world processes are dynamic in nature textiti.e., their characteristics vary with time. Thus it is not possible to train and tackle all possible distributional shifts between training and inference, using the host of transfer learning methods in literature. In this paper, we tackle this problem of adapting to domain shift at inference time textiti.e., we do not change the training process, but quickly adapt the model at test-time to handle any domain shift. For this, we propose to enforce consistency of predictions of data sampled in the vicinity of test sample on the image manifold. On a host of test scenarios like dealing with corruptions (CIFAR-10-C and CIFAR-100-C), and domain adaptation (VisDA-C), our method is at par or significantly outperforms previous methods.