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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add CaPT | CoOp · Base-to-new avg 11 datasets | H: 74.84 -> 77.44 | Improved |
| add CaPT | KgCoOp · Base-to-new avg 11 datasets | H: 76.98 -> 77.83 | Improved |
| add CaPT | ProGrad · Base-to-new avg 11 datasets | H: 76.18 -> 77.75 | Improved |
| add CaPT | DAPT · Base-to-new avg 11 datasets | H: 72.71 -> 76.60 | Improved |
| add CaPT | DePT · Base-to-new avg 11 datasets | H: 78.85 -> 79.63 | Improved |
| add TCI conditioning | CoOp · Base-to-new avg 11 datasets | new accuracy: 69.68 -> 72.94 | Improved |
| add margin-ITM loss on top of TCI (ablation) | CoOp · Base-to-new avg 11 datasets | H: 76.91 -> 77.44 | Improved |
| use CLIP text encoder instead of Fasttext for TCI (ablation) | CaPT · Base-to-new avg 11 datasets | H: 75.46 -> 77.44 | Improved |
| use MLP Meta-Net instead of attention (ablation) | CaPT · Base-to-new avg 11 datasets | H: 75.43 -> 77.44 | Improved |
| use MLP Meta-Net instead of linear (ablation) | CaPT · Base-to-new avg 11 datasets | H: 76.31 -> 77.44 | Improved |
| add CaPT | CoOp · Cross-dataset generalization avg | accuracy: 65.25 -> 65.52 | Improved |
| add CaPT | DePT · Cross-dataset generalization avg | accuracy: 65.36 -> 65.70 | Improved |
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.
- MaPLe — MaPLe: Multi-Modal Prompt Learning (CVPR 2023) · better on 1 of 1 shared result
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
- Learning to Learn Better Visual Prompts (AAAI 2024 · similarity 0.93)
- Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior (AAAI 2024 · similarity 0.92)
- Black-Box Test-Time Prompt Tuning for Vision-Language Models (AAAI 2025 · similarity 0.92)
- IPO: Interpretable Prompt Optimization for Vision-Language Models (NeurIPS 2024 · similarity 0.92)
- LaViP: Language-Grounded Visual Prompting (AAAI 2024 · similarity 0.91)
- ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models (CVPR 2024 · similarity 0.91)
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.
