Research map / Vision-language and multimodal / CLIP and zero-shot
Prompt-Robust Vision-Language Models via Meta-Finetuning
Haohui Liang, Runlin Huang, Yingjun Du, Yujia Hu, Weifeng Su, Cees G. M. Snoek
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 |
|---|---|---|---|
| apply Promise meta-finetuning on top of existing prompt learners | IVLP, MaPLe, MMRL · Base-to-new (11 datasets avg) | Harmonic mean H: MaPLe 78.55 -> 80.29; MMRL 81.20 -> 82.33; IVLP 77.66 -> 79.16 | Improved |
| add adaptive prompt weighting (ablation) | Promise on MaPLe · Base-to-new (11 datasets avg) | Harmonic mean H: 79.24 -> 80.29 | Improved |
| add adaptive prompt weighting (ablation) | Promise on MMRL · Base-to-new (11 datasets avg) | Harmonic mean H: 81.53 -> 82.33 | Improved |
| use token-specific learning rate instead of fixed rate (ablation) | Promise on MaPLe · Base-to-new (11 datasets avg) | Harmonic mean H: 79.08 -> 80.29 | Improved |
| use token-specific learning rate instead of task-specific (MetaSGD) rate (ablation) | Promise on MMRL · Base-to-new (11 datasets avg) | Harmonic mean H: 81.48 -> 82.33 | Improved |
| use both inner and outer loops rather than only one (ablation) | Promise on MaPLe · Base-to-new (11 datasets avg) | Harmonic mean H: 79.08 -> 80.29 (vs inner-only) | Improved |
| use full Promise instead of simple variance regularization (ablation) | MMRL · Base-to-new (11 datasets avg) | Harmonic mean H: 81.44 -> 82.33 | Improved |
| replace hand-crafted CLIP templates with LLM-generated templates for meta-finetuning (ablation) | Promise on MaPLe · Base-to-new (11 datasets avg) | Harmonic mean H: 80.29 -> 81.74 | Improved |
| increase template pool from 60 to 80 or 100 (ablation) | Promise on MMRL · Base-to-new (11 datasets avg) | Harmonic mean H: 82.33 -> 82.39 (80), 82.29 (100) | No clear effect |
| reduce template pool from 60 to 30 (ablation) | Promise on MMRL · Base-to-new (11 datasets avg) | Harmonic mean H: 82.33 -> 81.89 | Hurt |
| allow 20% overlap between inner and outer prompt sets (ablation) | Promise · Base-to-new (11 datasets avg) | Harmonic mean H: 80.31 -> 80.07 | No clear effect |
| apply Promise to SigLIP and BLIP-2 backbones | MaPLe, MMRL · Base-to-new SigLIP/BLIP-2 (11 datasets avg) | Harmonic mean H: SigLIP MaPLe 79.50 -> 80.84; BLIP-2 MMRL 81.07 -> 82.30 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- MMRL — MMRL: Multi-Modal Representation Learning for Vision-Language Models (CVPR 2025) · better on 3 of 3 shared results
- FedMVP — FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models (ICCV 2025) · better on 1 of 2 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
- IPO: Interpretable Prompt Optimization for Vision-Language Models (NeurIPS 2024 · similarity 0.93)
- Prompt Learning via Meta-Regularization (CVPR 2024 · similarity 0.93)
- Learning to Learn Better Visual Prompts (AAAI 2024 · similarity 0.92)
- Consistency-guided Prompt Learning for Vision-Language Models (ICLR 2024 · similarity 0.92)
- Language Models as Black-Box Optimizers for Vision-Language Models (CVPR 2024 · similarity 0.92)
- CoPL: Contextual Prompt Learning for Vision-Language Understanding (AAAI 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.
