mlsanityData to 14 Oct 2026

Temporal Test-Time Adaptation with State-Space Models

arXiv 2407.12492 ↗First posted 17 Jul 2024cs.LG cs.AI cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Distribution shifts between training and test data are inevitable over the lifecycle of a deployed model, leading to performance decay. Adapting a model on test samples can help mitigate this drop in performance. However, most test-time adaptation methods have focused on synthetic corruption shifts, leaving a variety of distribution shifts underexplored. In this paper, we focus on distribution shifts that evolve gradually over time, which are common in the wild but challenging for existing methods, as we show. To address this, we propose STAD, a Bayesian filtering method that adapts a deployed model to temporal distribution shifts by learning the time-varying dynamics in the last set of hidden features. Without requiring labels, our model infers time-evolving class prototypes that act as a dynamic classification head. Through experiments on real-world temporal distribution shifts, we show that our method excels in handling small batch sizes and label shift.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 69 of its 99 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

69 of 99 references.

References · 69

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  6. 2016Wide Residual Networkscited by 3,070
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  9. 2019Invariant Risk Minimizationcited by 1,854
  10. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  11. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  12. 2020In Search of Lost Domain Generalizationcited by 1,054
38 more
  1. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  2. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  3. 2021Domain Generalization: A Surveycited by 764
  4. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  5. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  6. 2022Continual Test-Time Domain Adaptationcited by 525
  7. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  8. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
  9. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
  10. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  11. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  12. 2017Functional Map of the Worldcited by 338
  13. 2022Contrastive Test-Time Adaptationcited by 261
  14. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
  15. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  16. 2022Parameter-free Online Test-time Adaptationcited by 189
  17. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 189
  18. 2015Deep Kalman Filterscited by 166
  19. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 156
  20. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 151
  21. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  22. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  23. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  24. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  25. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 104
  26. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
  27. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  28. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 90
  29. 2019Hyperspherical Prototype Networkscited by 86
  30. 2024Test-Time Model Adaptation with Only Forward Passescited by 74
  31. 2023DELTA: degradation-free fully test-time adaptationcited by 72
  32. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 67
  33. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
  34. 2022Test-Time Adaptation via Self-Training with Nearest Neighbor Informationcited by 64
  35. 2023On Pitfalls of Test-Time Adaptationcited by 64
  36. 2015A Century of Portraits: A Visual Historical Record of American High School Yearbookscited by 54
  37. 2023RDumb: A simple approach that questions our progress in continual test-time adaptationcited by 53
  38. 2017Incremental Adversarial Domain Adaptation for Continually Changing Environmentscited by 52

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025Monitoring Risks in Test-Time Adaptationcited by 11
  2. 2026TEFL: Prediction-Residual-Guided Rolling Forecasting for Multi-Horizon Time Seriescited by 2
  3. 2026PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devicescited by 2
  4. 2025TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traversescited by 0
  5. 2026A Non-Invasive Alternative to RFID: Self-Sufficient 3D Identification of Group-Housed Livestockcited by 0
  6. 2026A probabilistic framework for online test-time adaptationcited by 0
  7. 2026Online Learning via Learned Latent Bayesian Trackingcited by 0