AI Paper Atlas

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

Attention to the Burstiness in Visual Prompt Tuning!

Yuzhu Wang, Manni Duan, Shu Kong

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Parameter-efficient visual tuning · 3 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 SPT prompts with whitened bursty prompts (BPT-fWhiten) (ablation)SPT · ImageNet-1K (ablation, MAE ViT-B shallow)top-1 accuracy: 69.98 -> 72.09Improved
tune the whitening matrix (ablation)BPT-fWhiten · ImageNet-1K (ablation, MAE ViT-B shallow)top-1 accuracy: 72.09 -> 72.37Improved
use random-init bilinear prompt instead of tuned whitening (ablation)BPT-tWhiten · ImageNet-1K (ablation, MAE ViT-B shallow)top-1 accuracy: 72.37 -> 72.15No clear effect
increase prompt length from 64 to 196 (ablation)BPT-bilinear · ImageNet-1K (ablation, MAE ViT-B shallow)top-1 accuracy: 71.92 -> 72.48Improved
increase prompt width from 25 to 100 (ablation)BPT-bilinear · ImageNet-1K (ablation, MAE ViT-B shallow)top-1 accuracy: 72.06 -> 72.18Improved
increase prompt width from 25 to 100 (ablation)BPT-bilinear · CUB-200 (ablation, MAE ViT-B shallow)top-1 accuracy: 76.54 -> 78.59Improved
extend shallow to deep prompts in 4 blocks (ablation)BPT-bilinear · ImageNet-1K (ablation, MAE ViT-B)top-1 accuracy: 72.15 -> 74.25Improved
insert prompts in all 12 blocks rather than 4 (ablation)BPT-Deep · ImageNet-1K (ablation, MAE ViT-B)top-1 accuracy: 74.25 -> 74.73Improved
insert prompts in 3 blocks rather than 4 (ablation)BPT-Deep · ImageNet-1K (ablation, MAE ViT-B)top-1 accuracy: 74.25 -> 74.07Hurt
replace SPT-Deep with BPT-DeepSPT-Deep · ImageNet-1K (ablation, MAE ViT-B)top-1 accuracy: 73.34 -> 74.25Improved
replace SPT-S with BPT-S under MAESPT-S · FGVC mean (5 datasets, MAE pretrained ViT-B)mean accuracy: 73.95 -> 80.39Improved
replace SPT-S with BPT-S under MoCo-v3SPT-S · FGVC mean (5 datasets, MoCo-v3 pretrained ViT-B)mean accuracy: 84.08 -> 85.05Improved

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