# Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization

arXiv: https://arxiv.org/abs/2312.10165 · HTML: https://mlsanity.com/paper/2312.10165/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 15 Dec 2023.

## Builds on (most cited first, 30 of 37)

- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Which Tasks Should Be Learned Together in Multi-task Learning?](https://mlsanity.com/paper/1905.07553/) (2019)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Generalisation in humans and deep neural networks](https://mlsanity.com/paper/1808.08750/) (2018)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Adaptive Risk Minimization: Learning to Adapt to Domain Shift](https://mlsanity.com/paper/2007.02931/) (2020)
- [Learning to Optimize Domain Specific Normalization for Domain Generalization](https://mlsanity.com/paper/1907.04275/) (2019)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [Improved Few-Shot Visual Classification](https://mlsanity.com/paper/1912.03432/) (2019)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation](https://mlsanity.com/paper/2302.05155/) (2023)
- [The iWildCam 2021 Competition Dataset](https://mlsanity.com/paper/2105.03494/) (2021)

## Built on by (most cited first, 30 of 31)

- [Adapting to Distribution Shift by Visual Domain Prompt Generation](https://mlsanity.com/paper/2405.02797/) (2024)
- [Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2506.17307/) (2025)
- [Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams](https://mlsanity.com/paper/2407.12128/) (2024)
- [How to Train the Teacher Model for Effective Knowledge Distillation](https://mlsanity.com/paper/2407.18041/) (2024)
- [Plug-in Feedback Self-adaptive Attention in CLIP for Training-free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2508.20265/) (2025)
- [Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs](https://mlsanity.com/paper/2512.19918/) (2025)
- [Approximate Domain Unlearning for Vision-Language Models](https://mlsanity.com/paper/2510.08132/) (2025)
- [Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers](https://mlsanity.com/paper/2405.03730/) (2024)
- [ASMIL: Attention-Stabilized Multiple Instance Learning for Whole Slide Imaging](https://mlsanity.com/paper/2603.06658/) (2026)
- [Attention Bootstrapping for Multi-Modal Test-Time Adaptation](https://mlsanity.com/paper/2503.02221/) (2025)
- [On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning](https://mlsanity.com/paper/2410.04682/) (2024)
- [Test-time Correlation Alignment](https://mlsanity.com/paper/2505.00533/) (2025)
- [DDFP: Data-dependent Frequency Prompt for Source Free Domain Adaptation of Medical Image Segmentation](https://mlsanity.com/paper/2505.09927/) (2025)
- [DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning](https://mlsanity.com/paper/2501.12898/) (2025)
- [ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate](https://mlsanity.com/paper/2508.13445/) (2025)
- [MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning](https://mlsanity.com/paper/2505.20513/) (2025)
- [Saccadic Vision for Fine-Grained Visual Classification](https://mlsanity.com/paper/2509.15688/) (2025)
- [CRoP: Context-wise Robust Static Human-Sensing Personalization](https://mlsanity.com/paper/2409.17994/) (2024)
- [FRET: Feature Redundancy Elimination for Test Time Adaptation](https://mlsanity.com/paper/2505.10641/) (2025)
- [Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning](https://mlsanity.com/paper/2510.13865/) (2025)
- [TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery](https://mlsanity.com/paper/2603.08075/) (2026)
- [One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model](https://mlsanity.com/paper/2606.19718/) (2026)
- [From Visual Widgets to UI Code: Efficient Tool-Grounded Generation](https://mlsanity.com/paper/2608.12611/) (2026)
- [ELF-UA: Efficient Label-Free User Adaptation in Gaze Estimation](https://mlsanity.com/paper/2406.09481/) (2024)
- [Contrastive Residual Energy Test-time Adaptation](https://mlsanity.com/paper/2505.19607/) (2025)
- [When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class](https://mlsanity.com/paper/2506.15381/) (2025)
- [Test Time Adaptation Using Adaptive Quantile Recalibration](https://mlsanity.com/paper/2511.03148/) (2025)
- [Learning through Creation: A Hash-Free Framework for On-the-Fly Category Discovery](https://mlsanity.com/paper/2603.13858/) (2026)
- [DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation](https://mlsanity.com/paper/2607.17467/) (2026)
- [Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation](https://mlsanity.com/paper/2608.19890/) (2026)

## Abstract (arXiv)

Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight matrix and batch normalization (BN) layer. Previous works normally update the whole network naively without explicitly decoupling the knowledge between label and domain. As a result, it leads to knowledge interference and defective distribution adaptation. In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer. However, the normalization step in BN is intrinsically unstable when the statistics are re-estimated from a few samples. We find that ambiguities can be greatly reduced when only updating the two affine parameters in BN while keeping the source domain statistics. To further enhance the domain knowledge extraction from unlabeled data, we construct an auxiliary branch with label-independent self-supervised learning (SSL) to provide supervision. Moreover, we propose a bi-level optimization based on meta-learning to enforce the alignment of two learning objectives of auxiliary and main branches. The goal is to use the auxiliary branch to adapt the domain and benefit main task for subsequent inference. Our method keeps the same computational cost at inference as the auxiliary branch can be thoroughly discarded after adaptation. Extensive experiments show that our method outperforms the prior works on five WILDS real-world domain shift datasets. Our method can also be integrated with methods with label-dependent optimization to further push the performance boundary. Our code is available at https://github.com/ynanwu/MABN.