AI Paper Atlas

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

Progressive Visual Prompt Learning with Contrastive Feature Re-formation

Xu Chen, Yuhan Zhu, Haocheng Shen, Boheng Chen, Yixuan Liao, Xiaoxin Chen, Limin Wang

IJCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 59 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 contrastive feature re-formation loss to ProVP (ablation)ProVP · Base-to-new (11 datasets avg)new accuracy: 69.57 -> 73.22Improved
add contrastive feature re-formation loss to ProVP (ablation)ProVP · Base-to-new (11 datasets avg)harmonic mean: 76.57 -> 78.76Improved
add contrastive feature re-formation loss to ProVP (ablation)ProVP · Base-to-new (11 datasets avg)base accuracy: 85.14 -> 85.20No clear effect
use lambda=1.0 re-formation weight instead of 0 (ablation)ProVP-Ref · Base-to-new (DTD)new accuracy: 52.82 -> 59.06Improved
use lambda=0.8 re-formation weight instead of 0 (ablation)ProVP-Ref · Base-to-new (StanfordCars)harmonic mean: 71.03 -> 73.71Improved
use lambda=1.0 re-formation weight instead of 0 (ablation)ProVP-Ref · Base-to-new (DTD)base accuracy: 84.76 -> 83.95Hurt
use lambda=1.0 re-formation weight instead of 0 (ablation)ProVP-Ref · DTD 16-shotaccuracy: 73.70 -> 73.62No clear effect
use alpha=0.1 instead of 0.9 progressive decay (ablation)ProVP-Ref · DTD 16-shotaccuracy: 61.96 -> 73.62Improved
use alpha=0.1 instead of 0.01 progressive decay (ablation)ProVP-Ref · StanfordCars 16-shotaccuracy: 82.88 -> 84.85Improved
use alpha=0.1 instead of 0.9 progressive decay (ablation)ProVP-Ref · StanfordCars 16-shotaccuracy: 69.04 -> 84.85Improved
use ProVP-Ref instead of CoCoOpCLIP ViT-B/16 · Cross-dataset transfer (ImageNet source, 10 targets avg)accuracy: 65.74 -> 66.49Improved
use ProVP-Ref instead of CoOpCLIP ViT-B/16 · Cross-dataset transfer (EuroSAT target)accuracy: 46.39 -> 51.95Improved

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