AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

CVPT: Cross Visual Prompt Tuning

Lingyun Huang, Jianxu Mao, Junfei Yi, Ziming Tao, Yaonan Wang

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Efficient ViT adaptation · 8 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 concatenated prompts with cross-attention promptsVPT-Deep · VTAB-1k avgaccuracy: 72.0 -> 77.2Improved
replace concatenated prompts with cross-attention promptsVPT · FGVC avgaccuracy: 89.1 -> 90.5Improved
replace concatenated prompts with cross-attention promptsVPT · ADE20K ViT-LmIoU-SS: 42.11 -> 45.66Improved
use cross-attention with 200 prompts instead of VPT (ablation)VPT · VTAB-1k avg (200 prompts)accuracy: 64.0 -> 74.8Improved
use cross-attention with 1 prompt instead of VPT (ablation)VPT · VTAB-1k avg (1 prompt)accuracy: 71.0 -> 69.5Hurt
use cross-attention with 200 prompts instead of VPT (ablation)VPT · CIFAR-100 VTAB-1kaccuracy: 35.7 -> 72.1Improved
increase prompt count from 1 to 200 (ablation)CVPT · VTAB-1k avgaccuracy: 69.5 -> 74.8Improved
increase prompt count from 5 to 200 (ablation)VPT · VTAB-1k avgaccuracy: 73.0 -> 64.0Hurt
add weight sharing from self-attention to cross-attention (frozen CA) (ablation)CVPT · VTAB-1k avgaccuracy: 63.7 -> 74.0Improved
add weight sharing to learnable cross-attention (ablation)CVPT · VTAB-1k avgaccuracy: 74.0 -> 74.6Improved
freeze shared cross-attention instead of making it learnable (ablation)CVPT · VTAB-1k avgaccuracy: 74.6 -> 74.0No clear effect
use CVPT instead of DM-LoRACVPT · VTAB-1k avgaccuracy: 77.0 -> 77.2Improved

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