AI Paper Atlas

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

LoGoPrompt: Synthetic Text Images Can Be Good Visual Prompts for Vision-Language Models

Cheng Shi, Sibei Yang

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 30 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
use synthetic class-name text images as visual prompts with min-max contrastive prompt selection, versus CoCoOpLoGoPrompt · Base-to-new, 11 dataset averageharmonic mean: 75.83 -> 79.03Improved
use class-wise synthetic visual prompts rather than learned visual prompts (VPT, DPT)CLIP base-to-new · Base-to-new, new-class accuracynew-class accuracy: +3.88%Improved
replace learned pixel-perturbation Visual Prompting with LoGoPromptCLIP RN50 few-shot · 16-shot, 11 dataset averageaccuracy: 61.84 -> 76.31Improved
add feature adapter to LoGoPromptLoGoPrompt · 16-shot, 11 dataset averageaccuracy: 76.31 -> 77.28Improved
apply LoGoPrompt instead of CoCoOp for domain generalizationCLIP ViT-B/16 · ImageNet to V2/Sketch/A/Rtarget average accuracy: 62.13 -> 63.82Improved
treat synthetic text images as extra training images (no prompt selection) (ablation)LoGoPrompt · ImageNet 16-shot RN50accuracy: 63.12No clear effect
add visual prompt selection with min-max contrastive loss versus paired text-image (ablation)LoGoPrompt · ImageNet 16-shot RN50accuracy: 63.54 -> 66.34Improved
use too large a visual prompt (ratio 2/7 vs 1/7) (ablation)LoGoPrompt · ImageNet 16-shot RN50accuracy: 66.34 -> 66.17Hurt
use random location for visual prompt instead of fixed (ablation)LoGoPrompt · ImageNet 16-shot RN50accuracy: 66.01 -> 66.34Improved
increase text prompt length M from 2 to 16 (ablation)LoGoPrompt · ImageNet 16-shot RN50accuracy: 65.58 -> 66.34Improved

Later papers that compared with this method

1 later accepted paper reports LoGoPrompt as a baseline in their results tables; 1 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