# Test-Time Training with Self-Supervision for Generalization under Distribution Shifts

arXiv: https://arxiv.org/abs/1909.13231 · HTML: https://mlsanity.com/paper/1909.13231/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2019.

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

- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [Deep Stable Learning for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2104.07876/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Visual Prompt Tuning for Test-time Domain Adaptation](https://mlsanity.com/paper/2210.04831/) (2022)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Generalizing Graph Neural Networks on Out-Of-Distribution Graphs](https://mlsanity.com/paper/2111.10657/) (2021)
- [Back to the Source: Diffusion-Driven Test-Time Adaptation](https://mlsanity.com/paper/2207.03442/) (2022)
- [RDumb: A simple approach that questions our progress in continual test-time adaptation](https://mlsanity.com/paper/2306.05401/) (2023)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [Noether Networks: Meta-Learning Useful Conserved Quantities](https://mlsanity.com/paper/2112.03321/) (2021)
- [Debiased Graph Neural Networks with Agnostic Label Selection Bias](https://mlsanity.com/paper/2201.07708/) (2022)
- [Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks](https://mlsanity.com/paper/2105.08714/) (2021)
- [Test-Time Training for Deformable Multi-Scale Image Registration](https://mlsanity.com/paper/2103.13578/) (2021)
- [Test-Time Training for Graph Neural Networks](https://mlsanity.com/paper/2210.08813/) (2022)
- [The Future of Continual Learning in the Era of Foundation Models: Three Key Directions](https://mlsanity.com/paper/2506.03320/) (2025)
- [Few-Shot Adaptation of Pre-Trained Networks for Domain Shift](https://mlsanity.com/paper/2205.15234/) (2022)
- [MoVie: Visual Model-Based Policy Adaptation for View Generalization](https://mlsanity.com/paper/2307.00972/) (2023)
- [Dual Test-time Training for Out-of-distribution Recommender System](https://mlsanity.com/paper/2407.15620/) (2024)
- [On-target Adaptation](https://mlsanity.com/paper/2109.01087/) (2021)
- [Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series](https://mlsanity.com/paper/2202.02403/) (2022)
- [Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues](https://mlsanity.com/paper/2303.08106/) (2023)
- [SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization](https://mlsanity.com/paper/2511.17938/) (2025)
- [AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.10140/) (2021)
- [VPA: Fully Test-Time Visual Prompt Adaptation](https://mlsanity.com/paper/2309.15251/) (2023)
- [CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training](https://mlsanity.com/paper/2412.15646/) (2024)
- [Learning from Streaming Video with Orthogonal Gradients](https://mlsanity.com/paper/2504.01961/) (2025)
- [Image Restoration by Deep Projected GSURE](https://mlsanity.com/paper/2102.02485/) (2021)
- [Don't throw the baby out with the bathwater: How and why deep learning for ARC](https://mlsanity.com/paper/2506.14276/) (2025)
- [No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations](https://mlsanity.com/paper/2407.10964/) (2024)
- [Progressive Test Time Energy Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2503.16616/) (2025)

## Abstract (arXiv)

In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.