AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Hierarchical Variational Test-Time Prompt Generation for Zero-Shot Generalization

Zhaoyang Wu, Fang Liu, Licheng Jiao, Shuo Li, Lingling Li, Xu Liu, Puhua Chen, Wenping Ma

ICCV 2025 · 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
replace test-time prompt tuning with HyperTransformer prompt generation (ablation)MaPLe · ImageNet OOD average (ablation, MaPLe-based)accuracy: 62.31 -> 63.29Improved
add HyperTransformer prompt generation to MaPLe (ablation)MaPLe · ImageNet OOD average (ablation, MaPLe-based)accuracy: 60.28 -> 63.29Improved
add variational prompt generation to deterministic prompts (ablation)HyperTransformer MaPLe · ImageNet OOD average (ablation, MaPLe-based)accuracy: 63.29 -> 64.09Improved
add variational prompts on ImageNet-A (ablation)HyperTransformer MaPLe · ImageNet-Aaccuracy: 59.26 -> 60.71Improved
make variational prompts hierarchical (layer-conditioned) (ablation)HyperTransformer MaPLe · ImageNet OOD average (ablation, MaPLe-based)accuracy: 64.09 -> 65.89Improved
make variational prompts hierarchical on ImageNet-Sketch (ablation)HyperTransformer MaPLe · ImageNet-Sketchaccuracy: 50.41 -> 52.71Improved
make variational prompts hierarchical on ImageNet-R (ablation)HyperTransformer MaPLe · ImageNet-Raccuracy: 79.45 -> 81.45Improved
apply hierarchical variational prompt generation vs MaPLe+TPTMaPLe · Cross-dataset averageaccuracy: 66.50 -> 68.84Improved
apply hierarchical variational prompt generation vs strongest baseline DynaPromptDynaPrompt · ImageNet OOD averageaccuracy: 64.31 -> 65.89Improved
apply hierarchical variational prompt generation vs TDA on EuroSATTDA · EuroSATaccuracy: 58.00 -> 49.35Hurt

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