AI Paper Atlas

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

LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models

Adrian Bulat, Georgios Tzimiropoulos

CVPR 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 49 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 the text-to-text cross-entropy loss to CoOp (ablation)CoOp soft prompting · 11-dataset average, new classesaccuracy: 63.22 -> 71.54Improved
add grouped prompts to Text-to-Text (ablation)LASP · 11-dataset average, new classesaccuracy: 71.54 -> 73.48Improved
add visual/text re-alignment (ablation)Grouped LASP · 11-dataset average, new classesaccuracy: 73.48 -> 74.90Improved
add virtual class names during training (ablation)LASP · 11-dataset average, new classesaccuracy: 74.90 -> 76.11Improved
increase hand-crafted template count from 34 to 100 (ablation)Text-to-Text prompting · DTD new classesaccuracy: 52.10 -> 56.53Improved
replace hand-crafted templates with random templates (ablation)Text-to-Text prompting · DTD new classesaccuracy: 52.10 -> 51.63Hurt
replace text-to-text cross-entropy with L1 loss (ablation)LASP Text-to-Text objective · new classesaccuracy: 71.54 -> 66.01Hurt
replace text-to-text cross-entropy with L2 loss (ablation)LASP Text-to-Text objective · new classesaccuracy: 71.54 -> 65.80Hurt
train with virtual classes (ablation)LASP · EuroSAT new classesaccuracy: 77.78 -> 83.37Improved
train with virtual classes (ablation)LASP · OxfordPets new classesaccuracy: 97.93 -> 97.87No clear effect
train with virtual classes (ablation)LASP · Flowers102 new classesaccuracy: 74.0 -> 73.53Hurt
intermix template categories during training (ablation)LASP · novel classesaccuracy: 0.5%Hurt

Later papers that compared with this method

3 later accepted papers report LASP 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