AI Paper Atlas

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

FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models

Mainak Singha, Subhankar Roy, Sarthak Mehrotra, Ankit Jha, Moloud Abdar, Biplab Banerjee, Elisa Ricci

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 5 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 PromptFormer cross-attention prompts to CLIP (ablation)ZS-CLIP · Base-to-new (9 datasets avg)harmonic mean: 74.24 -> 75.94Improved
add consistency loss L_con (ablation)PromptFormer · Base-to-new (9 datasets avg)harmonic mean: 75.94 -> 76.27Improved
add LoRA fine-tuning of PromptFormer (ablation)FedMVP · Base-to-new (9 datasets avg)harmonic mean: 77.41 -> 78.27Improved
add PromptFormer cross-attention prompts to CLIP (ablation)ZS-CLIP · DomainBed MSST DG (avg 5 datasets)accuracy: 70.41 -> 71.85Improved
add consistency loss L_con (ablation)PromptFormer · DomainBed MSST DG (avg 5 datasets)accuracy: 71.85 -> 72.14Improved
add LoRA fine-tuning of PromptFormer (ablation)FedMVP · DomainBed MSST DG (avg 5 datasets)accuracy: 72.58 -> 73.02Improved
use visual prompting instead of textual prompting (ablation)FedMVP · Base-to-new (9 datasets avg)harmonic mean: 73.56 -> 78.27Improved
use visual prompting instead of multimodal prompting (ablation)FedMVP · DomainBed MSST DG (avg 5 datasets)accuracy: 69.14 -> 73.02Improved
use visual prompting instead of textual prompting (ablation)FedMVP · DomainBed SSMT DG (avg 5 datasets)accuracy: 65.89 -> 72.63Improved
use LLM attributes via PromptFormer cross-attention instead of DESC scoring aloneFedMVP · DomainBed MSST DG (avg 5 datasets)accuracy: 69.89 -> 72.24Improved
use LLM attributes via PromptFormer cross-attention instead of DESC scoring aloneFedMVP · Base-to-new (9 datasets avg)harmonic mean: 75.18 -> 77.52Improved
compare FedMVP against ZS-CLIP on OxfordPets and StanfordCars cross-datasetFedMVP · Cross-dataset generalizationaccuracy: -1.33 on OxfordPets, -4.56 on EuroSAT vs best baselineHurt

Later papers that compared with this method

1 later accepted paper reports FedMVP as a baseline in their results tables; 0 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