# MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption

arXiv: https://arxiv.org/abs/2103.16201 · HTML: https://mlsanity.com/paper/2103.16201/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 42 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 30 of 35)

- [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)
- [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)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [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)
- [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)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [Why do deep convolutional networks generalize so poorly to small image transformations?](https://mlsanity.com/paper/1805.12177/) (2018)
- [Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning](https://mlsanity.com/paper/2003.12862/) (2020)
- [A Review of Single-Source Deep Unsupervised Visual Domain Adaptation](https://mlsanity.com/paper/2009.00155/) (2020)
- [Deep Visual Domain Adaptation](https://mlsanity.com/paper/2012.14176/) (2020)
- [Unsupervised Learning via Meta-Learning](https://mlsanity.com/paper/1810.02334/) (2018)
- [When Does Self-supervision Improve Few-shot Learning?](https://mlsanity.com/paper/1910.03560/) (2019)
- [Unsupervised Meta-Learning For Few-Shot Image Classification](https://mlsanity.com/paper/1811.11819/) (2018)

## Built on by (most cited first, 30 of 65)

- [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)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Robust Mean Teacher for Continual and Gradual Test-Time Adaptation](https://mlsanity.com/paper/2211.13081/) (2022)
- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction](https://mlsanity.com/paper/2306.00650/) (2023)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [Test-Time Learning for Large Language Models](https://mlsanity.com/paper/2505.20633/) (2025)
- [Improved Test-Time Adaptation for Domain Generalization](https://mlsanity.com/paper/2304.04494/) (2023)
- [A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning](https://mlsanity.com/paper/2501.02497/) (2025)
- [If your data distribution shifts, use self-learning](https://mlsanity.com/paper/2104.12928/) (2021)
- [TTTFlow: Unsupervised Test-Time Training with Normalizing Flow](https://mlsanity.com/paper/2210.11389/) (2022)
- [Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback](https://mlsanity.com/paper/2311.16102/) (2023)
- [Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach](https://mlsanity.com/paper/2408.07511/) (2024)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [Test-Time Training for Graph Neural Networks](https://mlsanity.com/paper/2210.08813/) (2022)
- [What, How, and When Should Object Detectors Update in Continually Changing Test Domains?](https://mlsanity.com/paper/2312.08875/) (2023)
- [Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series](https://mlsanity.com/paper/2202.02403/) (2022)
- [Improving Domain Generalization with Domain Relations](https://mlsanity.com/paper/2302.02609/) (2023)
- [Learning Instance-Specific Adaptation for Cross-Domain Segmentation](https://mlsanity.com/paper/2203.16530/) (2022)
- [Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams](https://mlsanity.com/paper/2407.12128/) (2024)
- [Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection](https://mlsanity.com/paper/2505.19475/) (2025)
- [Introducing Intermediate Domains for Effective Self-Training during Test-Time](https://mlsanity.com/paper/2208.07736/) (2022)
- [Uncovering Adversarial Risks of Test-Time Adaptation](https://mlsanity.com/paper/2301.12576/) (2023)
- [Towards Task Sampler Learning for Meta-Learning](https://mlsanity.com/paper/2307.08924/) (2023)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation](https://mlsanity.com/paper/2505.20704/) (2025)
- [Test-Time Model Adaptation for Quantized Neural Networks](https://mlsanity.com/paper/2508.02180/) (2025)

## Abstract (arXiv)

An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however, breaks this paradigm and enables adaption at test-time. We combine meta-learning, self-supervision and test-time training to learn to adapt to unseen test distributions. By minimizing the self-supervised loss, we learn task-specific model parameters for different tasks. A meta-model is optimized such that its adaption to the different task-specific models leads to higher performance on those tasks. During test-time a single unlabeled image is sufficient to adapt the meta-model parameters. This is achieved by minimizing only the self-supervised loss component resulting in a better prediction for that image. Our approach significantly improves the state-of-the-art results on the CIFAR-10-Corrupted image classification benchmark. Our implementation is available on GitHub.