Test-Time Adaptation
Overview
Test-time adaptation studies how pretrained models can adjust to changing data during deployment, improving reliability when target labels or retraining are unavailable. Common approaches use entropy minimization, pseudo-labels, normalization or feature-statistics alignment, and lightweight prompts, adapters, caches, or memory; gradient-free methods aim to reduce compute and memory costs. Work spans image corruptions and domain shifts, medical imaging, time-series forecasting, language-model reasoning, and robotics. A central tension is that noisy self-generated signals can cause error accumulation or forgetting, so methods must determine when adaptation is useful and how to evaluate its benefits beyond average accuracy.
Latest papers
342 papers40 papers in the last four weeks, down 17% on the four weeks before. 0.3% of all new papers.
Test-time Adaptation for Point Cloud Denoising under Unseen Noise
IntriAdapt: Generalizable Intrinsic-Guided Test-Time Adaptation for Metric Geometry Estimation
Transport What Shares the Conduction Pathway: Normal-Anchored SPD Geometric Transport for Source-Free Patient Adaptation of Holter and Patch ECG
Hidden Trajectories Don't Lie: Correcting Corruption Drift for Test-Time Adaptation
Expand-and-Prune: Test-Time Candidate-Space Adaptation for End-to-End Autonomous Driving
Advancing Sentence-Level Dysarthric Audio-Visual Speech Recognition via Test-Time Adaptation
T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
CF-NODE: Counterfactual Spatial Node Intervention for Test-Time Adaptation Under Domain Shift, Evaluated Across Five Diabetic Retinopathy Datasets
SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token Routing
MMLA-RSI: Recursive Self-Improvement through RTT and RTMA
On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs
Frustratingly Easy Majority Voting Using Length Conditioning
PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
Mobility Helps Learning: Unsupervised Model Adaptation for Object Recognition via Movement
MoCaFe, a model-agnostic and hyperparameter-insensitive paradigm that leverages motion-induced prediction variance for unsupervised adaptation. Specifically, we first develop mobility-calibrated filtering of pseudo-labels, which constructs reliable pseudo-labels by fusing cross-view predictions using inverse-variance weights. The filtered pseudo-labels then guide the selection of ``hard samples'' for effective learning. To further suppress pseudo-label corruption, we introduce p-MoCaFe, an optional extension that uses a public dataset to assign weighting factors to data samples, yielding an estimator of the clean loss with bounded bias. Extensive experiments on autonomous driving (nuScenes, KITTI) and embodied-agent datasets show that MoCaFe significantly outperforms state-of-the-art TTA schemes, achieving up to approximately 20% accuracy gain.