mlsanityData to 14 Oct 2026

Test time Adaptation through Perturbation Robustness

arXiv 2110.10232 ↗First posted 19 Oct 2021cs.LG cs.CVcited by 28

Not on the map. Why?

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.

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

31 of 50 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2016Wide Residual Networkscited by 3,070
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  5. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  6. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  7. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  8. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  9. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
  10. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
19 more
  1. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  2. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  3. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  4. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  5. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  6. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  7. 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 359
  8. 2015Semi-Supervised Learning with Ladder Networkscited by 247
  9. 2014Learning with Pseudo-Ensemblescited by 241
  10. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
  11. 2018Sensitivity and Generalization in Neural Networks: an Empirical Studycited by 189
  12. 2018Large Margin Deep Networks for Classificationcited by 112
  13. 2017Learning to Compose Domain-Specific Transformations for Data Augmentationcited by 91
  14. 2020Unsupervised Domain Adaptation in Semantic Segmentation: a Reviewcited by 88
  15. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  16. 2019Understanding Generalization through Visualizationscited by 54
  17. 2017Adversarial Feature Augmentation for Unsupervised Domain Adaptationcited by 48
  18. 2021Robustness via Cross-Domain Ensemblescited by 23
  19. 2021Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistencycited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 8; 2025: 7; 2026: 1.

28 papers.

Sort:

By area:

  1. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  2. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  3. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  4. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  5. 2025Test-Time Learning for Large Language Modelscited by 50
  6. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 44
  7. 2023DomainAdaptor: A Novel Approach to Test-time Adaptationcited by 20
  8. 2024Uncertainty-Calibrated Test-Time Model Adaptation without Forgettingcited by 20
  9. 2022Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognitioncited by 19
  10. 2023Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?cited by 13
  11. 2025Noisy Test-Time Adaptation in Vision-Language Modelscited by 10
  12. 2025Test-Time Model Adaptation for Quantized Neural Networkscited by 10
16 more
  1. 2022Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptationcited by 9
  2. 2023REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptationcited by 7
  3. 2024Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptationcited by 3
  4. 2024LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognitioncited by 3
  5. 2025Single Image Test-Time Adaptation via Multi-View Co-Trainingcited by 3
  6. 2023Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentationcited by 2
  7. 2023Enhancing Plasticity for First Session Adaptation Continual Learningcited by 2
  8. 2023Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifierscited by 2
  9. 2024Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switchingcited by 2
  10. 2024Fully Test-Time Adaptation for Monocular 3D Object Detectioncited by 2
  11. 2025SEVA: Leveraging Single-Step Ensemble of Vicinal Augmentations for Test-Time Adaptationcited by 2
  12. 2025PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptationcited by 2
  13. 2026ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimizationcited by 2
  14. 2024Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignmentcited by 1
  15. 2024Improving Batch Normalization with TTA for Robust Object Detection in Self-Drivingcited by 1
  16. 2025Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codescited by 0