AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

A Probabilistic Framework for Lifelong Test-Time Adaptation

Dhanajit Brahma, Piyush Rai

CVPR 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 31 citations (OpenAlex)

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 the approximate source-model posterior regularizer and PETAL adaptation framework rather than CoTTALifelong test-time adaptation · CIFAR10-to-CIFAR10C, severity 5classification error (%): 16.29 (0.02) -> 15.95 (0.04)Improved
Add the approximate source-model posterior regularizer and PETAL adaptation framework rather than CoTTALifelong test-time adaptation · CIFAR100-to-CIFAR100C, severity 5classification error (%): 32.48 (0.02) -> 31.46 (0.04)Improved
Use FIM-driven parameter restoration instead of stochastic restoration (ablation)PETAL · CIFAR10-to-CIFAR10C, severity 5classification error (%): 16.16 (0.02) -> 15.95 (0.04)Improved
Use FIM-driven parameter restoration instead of stochastic restoration (ablation)PETAL · CIFAR100-to-CIFAR100C, severity 5classification error (%): 31.62 (0.04) -> 31.46 (0.04)Improved
Remove parameter restoration (ablation)PETAL · CIFAR10-to-CIFAR10Cclassification error (%): 15.95±0.04 -> 16.37±0.03Hurt
Use stochastic restoration at rate 0.03 instead of FIM-based restoration (ablation)PETAL · CIFAR10-to-CIFAR10Cclassification error (%): 15.95±0.04 -> 16.51±0.02Hurt
Add PETAL's posterior regularization and adaptation rather than CoTTALifelong test-time adaptation · CIFAR100-to-CIFAR100C, severity 5NLL: 1.2767 (0.0006) -> 1.2206 (0.0011)Improved
Add PETAL's posterior regularization and adaptation rather than CoTTALifelong test-time adaptation · CIFAR100-to-CIFAR100C, severity 5Brier: 0.4430 (0.0003) -> 0.4317 (0.0003)Improved
Add PETAL adaptation rather than CoTTALifelong test-time adaptation · ImageNet-to-ImageNetC, severity 5Error (%): 63.18 -> 62.71Improved
Add PETAL adaptation rather than CoTTALifelong test-time adaptation · ImageNet-to-ImageNet3DCC, severity 5Error (%): 59.91 -> 59.61Improved
Add PETAL adaptation rather than CoTTALifelong test-time adaptation · CIFAR10-to-CIFAR10C, gradually changing severityError (%): 10.40 ± 0.22 -> 10.11 ± 0.23Improved

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