Research map / Vision-language and multimodal / CLIP and zero-shot
AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning
Fei Song, Yi Li, Jiangmeng Li, Rui Wang, Changwen Zheng, Fanjiang Xu, Hui Xiong
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 HMPE and ADWG (AmPLe) to MaPLe (ablation) | MaPLe · Base-to-novel generalization | harmonic mean: HM 79.26 -> 80.28 | Improved |
| add ADWG on top of HMPE (ablation) | MaPLe + AmPLe · Base-to-novel generalization | harmonic mean: HM 80.05 -> 80.28 | Improved |
| add ADWG on top of HMPE (ablation) | MMA + AmPLe · Base-to-novel generalization | harmonic mean: HM 81.03 -> 81.11 | Improved |
| add ADWG on top of HMPE (ablation) | MMRL + AmPLe · Base-to-novel generalization | harmonic mean: HM 82.32 -> 82.56 | Improved |
| add HMPE and ADWG (AmPLe) to MMA (ablation) | MMA · Base-to-novel generalization | harmonic mean: HM 80.35 -> 81.11 | Improved |
| add AmPLe to MMRL (ablation) | MMRL · Base-to-novel generalization | harmonic mean: HM 82.06 -> 82.56 | Improved |
| add AmPLe to MaPLe | MaPLe · Cross-dataset generalization | average accuracy: 66.30 -> 67.15 | Improved |
| add AmPLe to MMA | MMA · Cross-dataset generalization | accuracy (%): 66.61 -> 66.88; +2.59% average gain | Improved |
| add AmPLe to MMRL | MMRL · Cross-dataset generalization | accuracy (%): 67.25 -> 68.87 | Improved |
| add AmPLe to MaPLe | MaPLe · Domain generalization | average accuracy: 60.28 -> 60.41 | Improved |
| add AmPLe to MMRL | MMRL · Domain generalization (ImageNet-A) | accuracy (%): -2.23 | Hurt |
| shuffle prompt order (ablation) | MMRL + AmPLe · Base-to-novel generalization | harmonic mean: SUN397 HM 82.29 -> 82.30 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MaPLe — MaPLe: Multi-Modal Prompt Learning (CVPR 2023) · better on 4 of 4 shared results
- MMRL — MMRL: Multi-Modal Representation Learning for Vision-Language Models (CVPR 2025) · better on 3 of 3 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
- IPO: Interpretable Prompt Optimization for Vision-Language Models (NeurIPS 2024 · similarity 0.91)
- Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation (ICLR 2025 · similarity 0.90)
- Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP (NeurIPS 2024 · similarity 0.90)
- CoPL: Contextual Prompt Learning for Vision-Language Understanding (AAAI 2024 · similarity 0.89)
- Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models (ICML 2024 · similarity 0.89)
- Learning to Prompt with Text Only Supervision for Vision-Language Models (AAAI 2025 · similarity 0.89)
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.
