# SITA: Single Image Test-time Adaptation

arXiv: https://arxiv.org/abs/2112.02355 · HTML: https://mlsanity.com/paper/2112.02355/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 36 references that are in the map.
- First posted on arXiv 4 Dec 2021.

## Builds on (most cited first, 27 of 27)

- [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)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [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)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [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)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Domain-Specific Batch Normalization for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1906.03950/) (2019)
- [Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data](https://mlsanity.com/paper/2010.03622/) (2020)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation](https://mlsanity.com/paper/2004.04668/) (2020)
- [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021)
- [MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption](https://mlsanity.com/paper/2103.16201/) (2021)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [MixNorm: Test-Time Adaptation Through Online Normalization Estimation](https://mlsanity.com/paper/2110.11478/) (2021)
- [SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth](https://mlsanity.com/paper/1612.05079/) (2016)

## Built on by (most cited first, 30 of 59)

- [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)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [Beyond Model Adaptation at Test Time: A Survey](https://mlsanity.com/paper/2411.03687/) (2024)
- [TTTFlow: Unsupervised Test-Time Training with Normalizing Flow](https://mlsanity.com/paper/2210.11389/) (2022)
- [DOTA: Distributional Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2409.19375/) (2024)
- [ClusT3: Information Invariant Test-Time Training](https://mlsanity.com/paper/2310.12345/) (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)
- [Unified Entropy Optimization for Open-Set Test-Time Adaptation](https://mlsanity.com/paper/2404.06065/) (2024)
- [ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation](https://mlsanity.com/paper/2309.05994/) (2023)
- [Learning Instance-Specific Adaptation for Cross-Domain Segmentation](https://mlsanity.com/paper/2203.16530/) (2022)
- [Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification](https://mlsanity.com/paper/2306.02544/) (2023)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [Unraveling Batch Normalization for Realistic Test-Time Adaptation](https://mlsanity.com/paper/2312.09486/) (2023)
- [MedBN: Robust Test-Time Adaptation against Malicious Test Samples](https://mlsanity.com/paper/2403.19326/) (2024)
- [Test-time Adaptation with Slot-Centric Models](https://mlsanity.com/paper/2203.11194/) (2022)
- [Medical Image Segmentation with InTEnt: Integrated Entropy Weighting for Single Image Test-Time Adaptation](https://mlsanity.com/paper/2402.09604/) (2024)
- [Test-time Batch Normalization](https://mlsanity.com/paper/2205.10210/) (2022)
- [REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation](https://mlsanity.com/paper/2309.03964/) (2023)
- [Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation](https://mlsanity.com/paper/2401.08328/) (2024)
- [Self-Bootstrapping for Versatile Test-Time Adaptation](https://mlsanity.com/paper/2504.08010/) (2025)
- [Adapting Prediction Sets to Distribution Shifts Without Labels](https://mlsanity.com/paper/2406.01416/) (2024)
- [Bi-TTA: Bidirectional Test-Time Adapter for Remote Physiological Measurement](https://mlsanity.com/paper/2409.17316/) (2024)
- [Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shifts](https://mlsanity.com/paper/2208.08767/) (2022)
- [Test-Time Training for Speech](https://mlsanity.com/paper/2309.10930/) (2023)

## Abstract (arXiv)

In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source. Crucially, TTA assumes no access to the source data or even any additional labeled/unlabeled samples from the target distribution to finetune the source model. In this work, we consider TTA in a more pragmatic setting which we refer to as SITA (Single Image Test-time Adaptation). Here, when making a prediction, the model has access only to the given single test instance, rather than a batch of instances, as typically been considered in the literature. This is motivated by the realistic scenarios where inference is needed on-demand instead of delaying for an incoming batch or the inference is happening on an edge device (like mobile phone) where there is no scope for batching. The entire adaptation process in SITA should be extremely fast as it happens at inference time. To address this, we propose a novel approach AugBN that requires only a single forward pass. It can be used on any off-the-shelf trained model to test single instances for both classification and segmentation tasks. AugBN estimates normalization statistics of the unseen test distribution from the given test image using only one forward pass with label-preserving transformations. Since AugBN does not involve any back-propagation, it is significantly faster compared to recent test time adaptation methods. We further extend AugBN to make the algorithm hyperparameter-free. Rigorous experimentation show that our simple algorithm is able to achieve significant performance gains for a variety of datasets, tasks, and network architectures.