AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Towards Stable Federated Continual Test-Time Adaptation in Wild World

Liwen Wang, Xingbo Dong, Iman Yi Liao, Zhe Jin

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add BPA (MAP-regularized local adaptation) instead of Tent (ablation)FedAvg global model · CIFAR10-Cmean accuracy (%): 64.72 -> 67.15Improved
add BPA instead of Tent (ablation)FedAvg global model · CIFAR100-Cmean accuracy (%): 57.51 -> 62.89Improved
add UGSA aggregation to Tent (without BPA) (ablation)Tent · Cityscapes-to-ACDC Seq4mean mIoU (%): 52.72 -> 58.12Improved
add UGSA aggregation to Tent (without BPA) (ablation)Tent · CIFAR10-Cmean accuracy (%): 64.72 -> 66.83Improved
combine BPA with UGSA (full method) vs BPA alone (ablation)BPFedCTTA · Cityscapes-to-ACDC Seq4mean mIoU (%): 58.30 -> 65.19Improved
combine BPA with UGSA (full method) vs BPA alone (ablation)BPFedCTTA · CIFAR100-C (ablation table)mean accuracy (%): 62.89 -> 64.57Improved
switch UGSA gating off (beta = 0.0) (ablation)BPFedCTTA · Cityscapes-to-ACDCStability (%): 62.9 -> 51.8Hurt
lower server learning rate gamma to 0.1 (ablation)UGSA · Cityscapes-to-ACDCPlasticity (%): 63.5 mIoU (gamma 0.5) -> 61.0 plasticityHurt
raise server learning rate gamma to 1.0 (ablation)UGSA · Cityscapes-to-ACDCStability (%): -> 59.0Hurt
replace predictive entropy with energy score for uncertainty in UGSA (ablation)UGSA · CIFAR10-Cmean accuracy (%): 68.44 -> 68.62Improved
replace predictive entropy with MC Dropout (T=10) or ensemble for uncertainty (ablation)UGSA · CIFAR10-Ctime per client (s): 4.492 -> 64.920 (MC Dropout); 4.492 -> 20.125 (Ensemble)Mixed
replace predictive entropy with max probability for uncertainty (ablation)UGSA · CIFAR10-Cmean accuracy (%): 68.44 -> 68.10Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy