mlsanityData to 13 Oct 2026

Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting

arXiv 2608.29920 ↗First posted 30 Aug 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA with batch size one and no access to source data is especially prone to drift or collapse. We introduce Sensitivity-Guided Erasing Adaptation (SEGA), a method for strict online continual TTA (CTTA) on corruption-style streams. SEGA uses a small number of structured erasures to probe how predictive entropy changes as information is removed, and uses the resulting per-sample sensitivity trajectories to coordinate recovery and sample selection rather than relying on raw entropy or batch statistics. This yields a practical feedback signal for long-horizon batch-size-one adaptation without periodic resets or model reservoirs. In experiments on ImageNet-C, CIFAR10/100-C, and corruption-generated aquaculture streams treated as controlled corruption-style proxies, SEGA yields consistent robustness and stability gains over strong CTTA baselines while reducing backward passes through sensitivity-based gating.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 30 Aug 2026.

Builds on

23 of 34 references.

References · 23

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,991
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,862
  4. 2022Continual Test-Time Domain Adaptationcited by 523
  5. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 429
  6. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 412
  7. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 376
  8. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
  9. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
  10. 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
  11. 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
  12. 2022Back to the Source: Diffusion-Driven Test-Time Adaptationcited by 71
11 more
  1. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
  2. 2021SITA: Single Image Test-time Adaptationcited by 59
  3. 2023RDumb: A simple approach that questions our progress in continual test-time adaptationcited by 52
  4. 2021If your data distribution shifts, use self-learningcited by 36
  5. 2024DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptationcited by 33
  6. 2023Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptationcited by 30
  7. 2025Ranked Entropy Minimization for Continual Test-Time Adaptationcited by 17
  8. 2025Monitoring Risks in Test-Time Adaptationcited by 10
  9. 2025ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domainscited by 9
  10. 2023SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptationcited by 8
  11. 2023REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptationcited by 7

Built on by

Not cited yet.