AI Paper Atlas

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

Diffusion-calibrated Continual Test-time Adaptation

Xu Yang, Moqi Li, Kun Wei

AAAI 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 0 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 generated-instance cross-entropy loss (CE1) (ablation)CE baseline · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 51.5 -> 46.8Improved
add reliable-instance selection and diversity weighting (WCE) (ablation)CE + CE1 · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 46.8 -> 43.2Improved
add contrastive learning with diffusion negatives (ablation)WCE · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 43.2 -> 38.3Improved
contrastive learning over all instances X instead of the full CL (ablation)WCE · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 41.8 vs 38.3Hurt
contrastive learning only on unselected instances (X \ S) (ablation)WCE · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 42.5 vs 38.3Hurt
contrastive learning only on selected instances S (ablation)WCE · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 41.2 vs 38.3Hurt
diffusion-calibrated supervision versus ROIDROID · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 45.0 -> 38.3Improved
diffusion-calibrated supervision versus REMREM · ImageNet-to-ImageNet-C (ViT-base)mean error rate (%): 39.2 -> 38.3Improved
diffusion-calibrated supervision versus ROIDROID · ImageNet-to-ImageNet-C (ResNet)mean error rate (%): 54.5 -> 50.2Improved
diffusion-calibrated supervision versus REMREM · CIFAR100-to-CIFAR100C (ViT-base)mean error rate (%): 23.4 -> 22.4Improved
diffusion-calibrated supervision versus REMREM · CIFAR10-to-CIFAR10C (ViT-base)mean error rate (%): 9.4 -> 8.7Improved
diffusion-calibrated supervision versus ROIDROID · CIFAR100-to-CIFAR100C (ResNet)mean error rate (%): 29.3 -> 26.7Improved

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