mlsanityData to 7 Oct 2026

Tent: Fully Test-time Adaptation by Entropy Minimization

arXiv 2006.10726 ↗First posted 18 Jun 2020cs.LG cs.CV stat.MLcited by 59

Not on the map. Why?

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.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 5; 2023: 11; 2024: 12; 2025: 7; 2026: 11.

59 papers.

Sort:

By area:

  1. 2021Predicting with Confidence on Unseen Distributionscited by 116
  2. 2023FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentationcited by 94
  3. 2021Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformationcited by 67
  4. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  5. 2023RDumb: A simple approach that questions our progress in continual test-time adaptationcited by 50
  6. 2021Self-Domain Adaptation for Face Anti-Spoofingcited by 49
  7. 2021Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentationcited by 39
  8. 2021If your data distribution shifts, use self-learningcited by 36
  9. 2021Test-Time Personalization with a Transformer for Human Pose Estimationcited by 33
  10. 2022Generative Domain Adaptation for Face Anti-Spoofingcited by 33
  11. 2021AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentationcited by 31
  12. 2021Noether Networks: Meta-Learning Useful Conserved Quantitiescited by 26
38 more
  1. 2022Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionarycited by 22
  2. 2021Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attackscited by 19
  3. 2024CLIPArTT: Adaptation of CLIP to New Domains at Test Timecited by 14
  4. 2021Towards Data-Free Domain Generalizationcited by 11
  5. 2023Cloud-Device Collaborative Learning for Multimodal Large Language Modelscited by 11
  6. 2021Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shiftcited by 9
  7. 2022Self-semantic contour adaptation for cross modality brain tumor segmentationcited by 9
  8. 2023Trust your Good Friends: Source-free Domain Adaptation by Reciprocal Neighborhood Clusteringcited by 9
  9. 2024CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Trainingcited by 9
  10. 2025RoboDriveVLM: A Novel Benchmark and Baseline towards Robust Vision-Language Models for Autonomous Drivingcited by 8
  11. 2026Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Trainingcited by 8
  12. 2022Unsupervised Domain Adaptation for Segmentation with Black-box Source Modelcited by 7
  13. 2023Monitoring and Adapting ML Models on Mobile Devicescited by 6
  14. 2025Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Modelscited by 6
  15. 2026Subspace Alignment for Vision-Language Model Test-time Adaptationcited by 5
  16. 2024Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonizationcited by 4
  17. 2025UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentationcited by 4
  18. 2025Adapting Like Humans: A Metacognitive Agent with Test-time Reasoningcited by 4
  19. 2021Black-Box Test-Time Shape REFINEment for Single View 3D Reconstructioncited by 3
  20. 2023Earning Extra Performance from Restrictive Feedbackscited by 3
  21. 2023Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReIDcited by 3
  22. 2024Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bankcited by 3
  23. 2024SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classificationcited by 3
  24. 2024A Bayesian Approach to OOD Robustness in Image Classificationcited by 3
  25. 2025Dream to Recall: Imagination-Guided Experience Retrieval for Memory-Persistent Vision-and-Language Navigationcited by 3
  26. 2021Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networkscited by 2
  27. 2023Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentationcited by 2
  28. 2023Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neurosciencecited by 2
  29. 2024TTAQ: Towards Stable Post-training Quantization in Continuous Domain Adaptationcited by 2
  30. 2024Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Losscited by 1
  31. 2025Unified 3D MRI Representations via Sequence-Invariant Contrastive Learningcited by 1
  32. 2026SC2-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environmentscited by 1
  33. 2026Test-Time Prototype Adaptation for Open-Vocabulary Semantic Segmentationcited by 1
  34. 2023SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistencycited by 0
  35. 2023Robust Source-Free Domain Adaptation for Fundus Image Segmentationcited by 0
  36. 2024Adversarial Reweighting with α-Power Maximization for Domain Adaptationcited by 0
  37. 2024Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptationcited by 0
  38. 2024Adaptify: A Refined Adaptation Scheme for Frame Classification in Atrophic Gastritis Videoscited by 0

50 most cited of 59 All 59 (JSON)