AI Paper Atlas

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

A Closer Look at Conditional Prompt Tuning for Vision-Language Models

Ji Zhang, Shihan Wu, Lianli Gao, Jingkuan Song, Nicu Sebe, Heng Tao Shen

IJCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 20 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 CaPTCoOp · Base-to-new avg 11 datasetsH: 74.84 -> 77.44Improved
add CaPTKgCoOp · Base-to-new avg 11 datasetsH: 76.98 -> 77.83Improved
add CaPTProGrad · Base-to-new avg 11 datasetsH: 76.18 -> 77.75Improved
add CaPTDAPT · Base-to-new avg 11 datasetsH: 72.71 -> 76.60Improved
add CaPTDePT · Base-to-new avg 11 datasetsH: 78.85 -> 79.63Improved
add TCI conditioningCoOp · Base-to-new avg 11 datasetsnew accuracy: 69.68 -> 72.94Improved
add margin-ITM loss on top of TCI (ablation)CoOp · Base-to-new avg 11 datasetsH: 76.91 -> 77.44Improved
use CLIP text encoder instead of Fasttext for TCI (ablation)CaPT · Base-to-new avg 11 datasetsH: 75.46 -> 77.44Improved
use MLP Meta-Net instead of attention (ablation)CaPT · Base-to-new avg 11 datasetsH: 75.43 -> 77.44Improved
use MLP Meta-Net instead of linear (ablation)CaPT · Base-to-new avg 11 datasetsH: 76.31 -> 77.44Improved
add CaPTCoOp · Cross-dataset generalization avgaccuracy: 65.25 -> 65.52Improved
add CaPTDePT · Cross-dataset generalization avgaccuracy: 65.36 -> 65.70Improved

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