# Tent: Fully Test-time Adaptation by Entropy Minimization

arXiv: https://arxiv.org/abs/2006.10726 · HTML: https://mlsanity.com/paper/2006.10726/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 30 of 69)

- [Predicting with Confidence on Unseen Distributions](https://mlsanity.com/paper/2107.03315/) (2021)
- [FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation](https://mlsanity.com/paper/2303.17225/) (2023)
- [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021)
- [Evaluating the Adversarial Robustness of Adaptive Test-time Defenses](https://mlsanity.com/paper/2202.13711/) (2022)
- [RDumb: A simple approach that questions our progress in continual test-time adaptation](https://mlsanity.com/paper/2306.05401/) (2023)
- [Self-Domain Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2102.12129/) (2021)
- [Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation](https://mlsanity.com/paper/2106.12497/) (2021)
- [If your data distribution shifts, use self-learning](https://mlsanity.com/paper/2104.12928/) (2021)
- [Test-Time Personalization with a Transformer for Human Pose Estimation](https://mlsanity.com/paper/2107.02133/) (2021)
- [Generative Domain Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2207.10015/) (2022)
- [AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation](https://mlsanity.com/paper/2110.12369/) (2021)
- [Noether Networks: Meta-Learning Useful Conserved Quantities](https://mlsanity.com/paper/2112.03321/) (2021)
- [Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary](https://mlsanity.com/paper/2206.14467/) (2022)
- [Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks](https://mlsanity.com/paper/2105.08714/) (2021)
- [CLIPArTT: Adaptation of CLIP to New Domains at Test Time](https://mlsanity.com/paper/2405.00754/) (2024)
- [Towards Data-Free Domain Generalization](https://mlsanity.com/paper/2110.04545/) (2021)
- [Cloud-Device Collaborative Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2312.16279/) (2023)
- [Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training](https://mlsanity.com/paper/2603.12255/) (2026)
- [Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shift](https://mlsanity.com/paper/2105.11804/) (2021)
- [Self-semantic contour adaptation for cross modality brain tumor segmentation](https://mlsanity.com/paper/2201.05022/) (2022)
- [Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clustering](https://mlsanity.com/paper/2309.00528/) (2023)
- [CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training](https://mlsanity.com/paper/2412.15646/) (2024)
- [RoboDriveVLM: A Novel Benchmark and Baseline towards Robust Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2512.01300/) (2025)
- [Unsupervised Domain Adaptation for Segmentation with Black-box Source Model](https://mlsanity.com/paper/2208.07769/) (2022)
- [Monitoring and Adapting ML Models on Mobile Devices](https://mlsanity.com/paper/2305.07772/) (2023)
- [Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2508.01225/) (2025)
- [Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning](https://mlsanity.com/paper/2511.23262/) (2025)
- [Subspace Alignment for Vision-Language Model Test-time Adaptation](https://mlsanity.com/paper/2601.08139/) (2026)
- [Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank](https://mlsanity.com/paper/2401.14619/) (2024)
- [Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization](https://mlsanity.com/paper/2407.15717/) (2024)

## Abstract (arXiv)

A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the entropy of its predictions. Our method estimates normalization statistics and optimizes channel-wise affine transformations to update online on each batch. Tent reduces generalization error for image classification on corrupted ImageNet and CIFAR-10/100 and reaches a new state-of-the-art error on ImageNet-C. Tent handles source-free domain adaptation on digit recognition from SVHN to MNIST/MNIST-M/USPS, on semantic segmentation from GTA to Cityscapes, and on the VisDA-C benchmark. These results are achieved in one epoch of test-time optimization without altering training.