AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer

Enming Zhang, Liwen Cao, Yanru Wu, Zhao Zijie, Yang Li

AAAI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical transfer learning · 0 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 H-score transferability objective to weight learning (no L_align) (ablation)HGPrompt · VTAB-1k ablation (Cifar, DTD, Pets, Euro average)avg accuracy: 72.5 -> 78.5Improved
add L_align gradient alignment to weight learning (no H-score) (ablation)HGPrompt · VTAB-1k ablation (Cifar, DTD, Pets, Euro average)avg accuracy: 72.5 -> 78.1Improved
add L_align on top of H-score (ablation)HGPrompt · VTAB-1k ablation (Cifar, DTD, Pets, Euro average)avg accuracy: 78.5 -> 80.0Improved
add H-score on top of L_align (ablation)HGPrompt · VTAB-1k ablation (Cifar, DTD, Pets, Euro average)avg accuracy: 78.1 -> 80.0Improved
HGPrompt versus strongest baseline PANDAmulti-source prompt transfer · VTAB-1k (13 tasks)avg accuracy: 58.7 -> 60.3Improved
HGPrompt versus PANDA on SVHNHGPrompt · VTAB-1k SVHNaccuracy: 71.2 -> 71.0Hurt
HGPrompt versus PANDA on Clevr-CountHGPrompt · VTAB-1k Clevr-Countaccuracy: 42.8 -> 49.3Improved
H-score based weights versus SPoT weights for predicting transferHGPrompt · Spearman correlation, 5 tasksSpearman rho avg: 0.105 -> 0.808Improved
H-score based weights versus PANDA weightsHGPrompt · Spearman correlation, 5 tasksSpearman rho avg: 0.569 -> 0.808Improved
increase number of source prompts from 3 to 11 (ablation)HGPrompt · VTAB-1k DTD targetaccuracyImproved
vary regularization coefficient lambda (ablation)HGPrompt · VTAB-1kaccuracyMixed

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