AI Paper Atlas

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

Dynamic Multimodal Prototype Learning in Vision-Language Models

Xingyu Zhu, Shuo Wang, Beier Zhu, Miaoge Li, Yunfan Li, Junfeng Fang, Zhicai Wang, Dongsheng Wang, Hanwang Zhang

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 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 Distributed Feature Construction (weighted augmented text and image distributions) to zero-shot CLIP (ablation)ProtoMM (RN50) · ImageNetaccuracy: 59.81 -> 60.82Improved
add Multimodal Prototype Learning (visual particles) on top of distributed features (ablation)ProtoMM (RN50) · ImageNetaccuracy: 60.82 -> 63.76Improved
add Multimodal Prototype Learning on top of distributed features (ablation)ProtoMM (ViT-B/16) · ImageNetaccuracy: 68.98 -> 72.01Improved
add Multimodal Prototype Learning on top of distributed features (ablation)ProtoMM (ViT-B/16) · Caltech101accuracy: 94.65 -> 95.70Improved
add Multimodal Prototype Learning on top of distributed features (ablation)ProtoMM (RN50) · Caltech101accuracy: 88.16 -> 89.94Improved
use ProtoMM instead of AWTCLIP RN50 · Cross-domain benchmark averageaccuracy: 62.17 -> 63.10Improved
use ProtoMM instead of DPECLIP ViT-B/16 · Cross-domain benchmark averageaccuracy: 69.62 -> 70.70Improved
use ProtoMM instead of DOTACLIP ViT-B/16 · ImageNet OOD averageaccuracy: 64.52 -> 65.69Improved
use ProtoMM instead of DPECLIP RN50 · Caltech101accuracy: 90.83 -> 89.94Hurt
use ProtoMM instead of AWTCLIP RN50 · Petsaccuracy: 88.22 -> 87.92Hurt
increase confidence threshold tau above 0.8 (ablation)ProtoMM · ImageNetaccuracyHurt
increase number of image or text augmentations beyond about 40 or 70 (ablation)ProtoMM · ImageNetaccuracyNo clear effect

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