AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Multi-modal Prototypes for Open-World Semantic Segmentation

Yuhuan Yang, Chaofan Ma, Chen Ju, Fei Zhang, Jiangchao Yao, Ya Zhang, Yanfeng Wang

IJCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 21 citations (OpenAlex)

Read the paper

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 text guidance to visual prototypes (full vs image only)Multi-modal prototype model · COCO-20i Z/FS (mean of 4 folds)mIoU: 43.4 -> 45.7Improved
add visual guidance to text-only modelMulti-modal prototype model · COCO-20i Z/FS (mean of 4 folds)mIoU: 26.9 -> 45.7Improved
add text to image-only modelMulti-modal prototype model · PASCAL-5i Z/FS (mean of 4 folds)mIoU: 63.9 -> 65.5Improved
multi-modal GFS vs DIaMOurs vs DIaM · PASCAL-5i GFS 1-shotUnSeen mIoU: 35.11 -> 39.44Improved
multi-modal GFS vs DIaMOurs vs DIaM · COCO-20i GFS 1-shotUnSeen mIoU: 17.22 -> 19.48Improved
increase visual prototypes from 1 to 5 (ablation)Multi-modal prototype model · PASCAL-5i GFS ablationHIoU: 39.39 -> 45.39Improved
decompose class names into 3 descriptions instead of 1 (ablation)Multi-modal prototype model · PASCAL-5i GFS ablationHIoU: 42.37 -> 44.17Improved
increase descriptions from 3 to 5 (ablation)Multi-modal prototype model · PASCAL-5i GFS ablationHIoU: 44.17 -> 42.89Hurt
add L=2 feature level to L=1 (ablation)Multi-modal prototype model · PASCAL-5i GFS ablationHIoU: 31.48 -> 39.99Improved
add L=3 feature level to L=1+2 (ablation)Multi-modal prototype model · PASCAL-5i GFS ablationHIoU: 39.99 -> 44.17Improved
use mask M-splitting instead of K-means for prototypes (ablation)Multi-modal prototype model · Mask splitting speedseconds per image: 22.9 -> 0.043Improved
use mask instead of box annotation for support (ablation)Multi-modal prototype model · PASCAL-5i GFS ablationHIoU: 35.00 -> 44.17Improved

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