AI Paper Atlas

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

Flatness Guided Test-Time Adaptation for Vision-Language Models

Aodi Li, Liansheng Zhuang, Xiao Long, Houqiang Li, Shafei Wang

ICLR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 2 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 sharpness-aware prompt tuning (SAPT) (ablation)CoOp · ImageNet + variants (Avg.)top-1 accuracy (%): 61.72 -> 62.64Improved
add sharpness-based test sample selection (STSS) (ablation)CoOp · ImageNet + variants (Avg.)top-1 accuracy (%): 61.72 -> 66.48Improved
add STSS on top of SAPT (full FGA) (ablation)CoOp+SAPT · ImageNet + variants (Avg.)top-1 accuracy (%): 62.64 -> 68.04Improved
add SAPT on top of STSS (ablation)CoOp+STSS · ImageNet + variants (Avg.)top-1 accuracy (%): 66.48 -> 68.04Improved
add SAPT on top of STSS (ablation)CoOp+STSS · ImageNet OOD (OOD Avg.)top-1 accuracy (%): 64.60 -> 66.55Improved
replace test-time prompt tuning with FGATPT+CoOp · ImageNet OOD (OOD Avg.)top-1 accuracy (%): 61.67 -> 66.55Improved
replace test-time prompt tuning with FGATPT+CoOp · Cross-dataset from ImageNet (10 datasets Avg.)top-1 accuracy (%): 65.66 -> 67.60Improved
use FGA instead of single-sample SARSAR+CoOp · ImageNet OOD (OOD Avg.)top-1 accuracy (%): 61.75 -> 66.55Improved
set test perturbation rho' to zero (entropy only, no sharpness) (ablation)FGA · ImageNet-Rtop-1 accuracy (%)Hurt
vary rho' (non-monotonic) (ablation)FGA · ImageNet-Rtop-1 accuracy (%)Mixed
retain more augmented samples (ablation)FGA · ImageNet-Rtop-1 accuracy (%)Mixed
FGA vs online TDA on cross-datasetTDA · Cross-dataset from ImageNet (10 datasets Avg.)top-1 accuracy (%): 67.53 -> 67.60Improved

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