AI Paper Atlas

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

IJCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 2 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 HMPE and ADWG (AmPLe) to MaPLe (ablation)MaPLe · Base-to-novel generalizationharmonic mean: HM 79.26 -> 80.28Improved
add ADWG on top of HMPE (ablation)MaPLe + AmPLe · Base-to-novel generalizationharmonic mean: HM 80.05 -> 80.28Improved
add ADWG on top of HMPE (ablation)MMA + AmPLe · Base-to-novel generalizationharmonic mean: HM 81.03 -> 81.11Improved
add ADWG on top of HMPE (ablation)MMRL + AmPLe · Base-to-novel generalizationharmonic mean: HM 82.32 -> 82.56Improved
add HMPE and ADWG (AmPLe) to MMA (ablation)MMA · Base-to-novel generalizationharmonic mean: HM 80.35 -> 81.11Improved
add AmPLe to MMRL (ablation)MMRL · Base-to-novel generalizationharmonic mean: HM 82.06 -> 82.56Improved
add AmPLe to MaPLeMaPLe · Cross-dataset generalizationaverage accuracy: 66.30 -> 67.15Improved
add AmPLe to MMAMMA · Cross-dataset generalizationaccuracy (%): 66.61 -> 66.88; +2.59% average gainImproved
add AmPLe to MMRLMMRL · Cross-dataset generalizationaccuracy (%): 67.25 -> 68.87Improved
add AmPLe to MaPLeMaPLe · Domain generalizationaverage accuracy: 60.28 -> 60.41Improved
add AmPLe to MMRLMMRL · Domain generalization (ImageNet-A)accuracy (%): -2.23Hurt
shuffle prompt order (ablation)MMRL + AmPLe · Base-to-novel generalizationharmonic mean: SUN397 HM 82.29 -> 82.30No 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.

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