Pith. sign in

REVIEW 14 cited by

Beyond Model Adaptation at Test Time: A Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.03687 v1 pith:GZOVJY7S submitted 2024-11-06 cs.LG cs.AI

classification cs.LGcs.AI
keywords adaptationtest-timedistributiondomaintestsurveytrainingacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Consequently, these algorithms struggle and become brittle even when samples in the test distribution start to deviate from the ones observed during training. Domain adaptation and domain generalization have been studied extensively as approaches to address distribution shifts across test and train domains, but each has its limitations. Test-time adaptation, a recently emerging learning paradigm, combines the benefits of domain adaptation and domain generalization by training models only on source data and adapting them to target data during test-time inference. In this survey, we provide a comprehensive and systematic review on test-time adaptation, covering more than 400 recent papers. We structure our review by categorizing existing methods into five distinct categories based on what component of the method is adjusted for test-time adaptation: the model, the inference, the normalization, the sample, or the prompt, providing detailed analysis of each. We further discuss the various preparation and adaptation settings for methods within these categories, offering deeper insights into the effective deployment for the evaluation of distribution shifts and their real-world application in understanding images, video and 3D, as well as modalities beyond vision. We close the survey with an outlook on emerging research opportunities for test-time adaptation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Respect Your Zero-Shot Uncertainty: Conservative Calibration for Test-Time-Adapted Vision-Language Models

    cs.CV 2026-08 conditional novelty 6.0 of 10

    ZAEC anchors calibration to each sample's zero-shot entropy and selectively softens over-sharpened TTA predictions, reaching the lowest macro-average calibration error among evaluated post-hoc methods on ViT-B/16.

  2. Family Matters: A Systematic Study of Spatial vs. Frequency Masking for Continual Test-Time Adaptation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Random spatial patch masking keeps continual test-time adaptation stable on long corrupted streams with ViTs, whereas random frequency-band masking collapses; the gap shrinks on CNNs and on global-cue tasks with large ViTs.

  3. Active Test-time Vision-Language Navigation

    cs.RO 2025-06 conditional novelty 6.0 of 10

    ATENA uses episodic success/failure labels and a mixture entropy objective to adapt vision-language navigation policies at test time, improving REVERIE, R2R, and R2R-CE benchmarks.

  4. Noise is an Efficient Learner for Zero-Shot Vision-Language Models

    cs.CV 2025-02 conditional novelty 6.0 of 10

    Optimizing a clamped Gaussian noise map on the input image at test time with entropy and inter-view consistency losses improves zero-shot CLIP accuracy on natural distribution shifts.

  5. Chaos Is a LADDER: Domain Generalization Beyond Invariance via Reweighting

    stat.ML 2026-07 conditional novelty 5.0 of 10

    Reweighting frozen source classifiers by target style-distribution distance (Sinkhorn-KNN) beats pooled and invariant predictors on some rule-varying DG benchmarks.

  6. Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Online dual distillation of a lightweight CLIP adapter (zero-shot prior plus frozen source adapter) yields state-of-the-art video test-time adaptation under severe natural domain shifts.

  7. Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

    cs.CV 2026-07 accept novelty 5.0 of 10

    CTTA methods fall into optimization-based, parameter-efficient, and architecture-based families that adapt pretrained vision models online under continual unlabeled shifts while fighting forgetting and error accumulation.

  8. Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces

    cs.HC 2026-01 conditional novelty 5.0 of 10

    A backpropagation-free test-time adaptation method, BFT, weights predictions from multiple transformed copies of each EEG test sample using a learning-to-rank module, improving cross-subject decoding without model updates.

  9. Adapting Vision-Language Models Without Labels: A Comprehensive Survey

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A survey that organizes unsupervised vision-language model adaptation by unlabeled-data availability into four paradigms: data-free transfer, domain transfer, episodic test-time, and online test-time adaptation.

  10. Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Latte improves federated test-time adaptation of CLIP by merging each client's local memory with prototypes retrieved from similar clients.

  11. Visual Instance-aware Prompt Tuning

    cs.CV 2025-07 conditional novelty 5.0 of 10

    ViaPT generates instance-aware prompts per image, fuses them with dataset-level prompts, and applies PCA compression to outperform VPT-Deep and other PEFT baselines on FGVC, HTA, and VTAB-1k.

  12. PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation

    cs.CV 2025-06 reject novelty 5.0 of 10

    PAID proposes Householder-based orthogonal weight updates for continual test-time adaptation, claiming that preserving pairwise angular structure of pretrained weights is a useful prior, but the math and validation fo...

  13. No Training, Better Flights: Test-Time Scaled VLMs for UAV Navigation

    cs.CV 2026-07 conditional novelty 4.0 of 10

    Test-time scaling—parallel candidate generation, iterative self-correction, and multi-criteria selection—improves a frozen UAV navigation VLM's success rate by about 2 percentage points on the TravelUAV benchmark.

  14. Continuous Self-Improvement of Large Language Models by Test-time Training with Verifier-Driven Sample Selection

    cs.CL 2025-05 reject novelty 4.0 of 10

    A test-time training method that fine-tunes LoRA adapters on verifier-selected high-confidence pseudo-labels, reporting large gains on math benchmarks, but evaluated on the same queries it adapts on.

Pith tools