AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning

Cheng Han, Qifan Wang, Yiming Cui, Zhiwen Cao, Wenguan Wang, Siyuan Qi, Dongfang Liu

ICCV 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation

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 key-value prompts in self-attention (ablation)E2VPT (visual prompts) · VTAB-1k SVHNaccuracy: 78.1% -> 83.8%Improved
add pruning and rewinding of input prompts (ablation)E2VPT (visual prompts) · VTAB-1k SVHNaccuracy: 78.1% -> 79.0%Improved
add pruning and rewinding on top of visual and key-value prompts (ablation)E2VPT · VTAB-1k SVHNaccuracy: 83.8% -> 85.3%Improved
add key-value prompts and pruning to visual prompts (ablation)E2VPT · FGVC NABirdsaccuracy: 84.2% -> 84.6%Improved
increase key-value prompts to 20 (versus 5) (ablation)E2VPT · VTAB-1k SVHNaccuracy: 85.3% -> 80.2%Hurt
place key-value prompts before rather than after K and V (ablation)E2VPT · VTAB-1kaverage accuracy: 73.91% -> 73.94%No clear effect
use He initialization instead of truncated normal (ablation)E2VPT · VTAB-1kaccuracy: Natural 79.77% -> 80.01%Mixed
replace VPT input-only prompts with E2VPT on MAE-pretrained ViTViT-Base MAE · VTAB-1k Naturalaccuracy: 36.02% -> 59.52%Improved

Later papers that compared with this method

2 later accepted papers report E2VPT as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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