mlsanityData to 7 Oct 2026

Unified Entropy Optimization for Open-Set Test-Time Adaptation

arXiv 2404.06065 ↗First posted 9 Apr 2024cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation (TTA) aims at adapting a model pre-trained on the labeled source domain to the unlabeled target domain. Existing methods usually focus on improving TTA performance under covariate shifts, while neglecting semantic shifts. In this paper, we delve into a realistic open-set TTA setting where the target domain may contain samples from unknown classes. Many state-of-the-art closed-set TTA methods perform poorly when applied to open-set scenarios, which can be attributed to the inaccurate estimation of data distribution and model confidence. To address these issues, we propose a simple but effective framework called unified entropy optimization (UniEnt), which is capable of simultaneously adapting to covariate-shifted in-distribution (csID) data and detecting covariate-shifted out-of-distribution (csOOD) data. Specifically, UniEnt first mines pseudo-csID and pseudo-csOOD samples from test data, followed by entropy minimization on the pseudo-csID data and entropy maximization on the pseudo-csOOD data. Furthermore, we introduce UniEnt+ to alleviate the noise caused by hard data partition leveraging sample-level confidence. Extensive experiments on CIFAR benchmarks and Tiny-ImageNet-C show the superiority of our framework. The code is available at https://github.com/gaozhengqing/UniEnt

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 50 of its 61 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

50 of 61 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  4. 2016Wide Residual Networkscited by 3,057
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2019Natural Adversarial Examplescited by 1,401
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  11. 2016An overview of gradient descent optimization algorithmscited by 1,021
  12. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
38 more
  1. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  2. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  3. 2021Domain Generalization: A Surveycited by 760
  4. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  5. 2021Domain Generalization with MixStylecited by 563
  6. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  7. 2022Continual Test-Time Domain Adaptationcited by 520
  8. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  9. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  10. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  11. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  12. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  13. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  14. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  15. 2021A Fourier-based Framework for Domain Generalizationcited by 287
  16. 2022Contrastive Test-Time Adaptationcited by 258
  17. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 235
  18. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  19. 2022Parameter-free Online Test-time Adaptationcited by 184
  20. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  21. 2018Reducing Network Agnostophobiacited by 165
  22. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  23. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 150
  24. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  25. 2019Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancycited by 112
  26. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  27. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  28. 2022Training OOD Detectors in their Natural Habitatscited by 86
  29. 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
  30. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 65
  31. 2021SITA: Single Image Test-time Adaptationcited by 57
  32. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  33. 2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
  34. 2023RDumb: A simple approach that questions our progress in continual test-time adaptationcited by 50
  35. 2023Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimizationcited by 39
  36. 2023On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansioncited by 34
  37. 2022Class-Specific Semantic Reconstruction for Open Set Recognitioncited by 28
  38. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 7; 2026: 7.

17 papers.

Sort:

By area:

  1. 2024COME: Test-time adaption by Conservatively Minimizing Entropycited by 31
  2. 2025Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimizationcited by 11
  3. 2025Active Test-time Vision-Language Navigationcited by 7
  4. 2024Temporal Test-Time Adaptation with State-Space Modelscited by 6
  5. 2025CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptationcited by 5
  6. 2024Efficient Open Set Single Image Test Time Adaptation of Vision Language Modelscited by 3
  7. 2025Stabilizing Open-Set Test-Time Adaptation via Primary-Auxiliary Filtering and Knowledge-Integrated Predictioncited by 1
  8. 2025CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Modelscited by 1
  9. 2025DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognitioncited by 1
  10. 2026Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptationcited by 1
  11. 2026Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directionscited by 1
  12. 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traversescited by 0
5 more
  1. 2026A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptationcited by 0
  2. 2026Cross-device Collaborative Test-time Adaptation with Zeroth-order Optimization and Model Mergingcited by 0
  3. 2026COSTA: A Cluster-Centric Paradigm for Annotation-Free Open-Set Semantic Segmentation of Aerial Point Clouds with Domain Shiftscited by 0
  4. 2026Reliable Neural Collapse Approximation for Open-World Test-Time Adaptationcited by 0
  5. 2026Test-Time Generalized Category Discoverycited by 0