AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Efficient Test-Time Prompt Tuning for Vision-Language Models

Yuhan Zhu, Guozhen Zhang, Xu Chen, Haocheng Shen, Xiaoxin Chen, Gangshan Wu, Limin Wang

IJCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 17 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 CPT during source prompt learning (ablation)CoOp · Base-to-new (Specialized)accuracy: 67.6 -> 70.5Improved
add test-time adaptation with CPT (ablation)CoOp+CPT · Base-to-new (Specialized)accuracy: 70.5 -> 73.3Improved
add gradient matching loss (ablation)CoOp+CPT+TTA · Base-to-new (Specialized)accuracy: 73.3 -> 74.9Improved
add Front view to CPT views (ablation)CPT · Base-to-new (Specialized)accuracy: 74.4 -> 74.9Improved
add Mid view to CPT views (ablation)CPT · Base-to-new (Specialized)accuracy: 73.9 -> 74.9Improved
add End view to CPT views (ablation)CPT · Base-to-new (Specialized)accuracy: 73.7 -> 74.9Improved
add hand-made prompt view to CPT (ablation)CPT · Base-to-new (Specialized)accuracy: 73.6 -> 74.9Improved
use cosine instead of MSE gradient matching (ablation)GM loss · Base-to-new (Specialized)accuracy: 73.9 -> 74.9Improved
add EMA to gradient matching (ablation)GM loss · Base-to-new (Specialized)accuracy: 73.4 -> 74.9Improved
combine MaPLe with TPTMaPLe · Cross-dataset generalizationaccuracy: 66.30 -> 66.50No clear effect
combine MaPLe with TPTMaPLe · Base-to-new generalizationaccuracy: 75.14 -> 74.95Hurt
combine CoOp with TPTCoOp · Base-to-new generalizationaccuracy: 73.06 -> 73.77Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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