AI Paper Atlas

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

Multi-Modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusion

Bing Cao, Yiming Sun, Pengfei Zhu, Qinghua Hu

ICCV 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 127 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 Mixture of Local Experts (MoLE) (ablation)MoE-Fusion · M3FDVIF: 0.8100 -> 1.0034Improved
add Mixture of Global Experts (MoGE) instead of a common decoder (ablation)MoE-Fusion · M3FDVIF: 0.8261 -> 1.0034Improved
use dynamic MoLE instead of attention-based local features (Att-Local) (ablation)MoE-Fusion · M3FDMI: 2.7320 -> 4.1949Improved
use fused images from MoE-Fusion for downstream detectionFaster R-CNN on FLIR · FLIR detectionmAP: 48.40 -> 55.80Improved
increase number of experts beyond 4 (E6K2, E8K2 vs E4K2) (ablation)MoE-Fusion · FLIRfusion metricsNo clear effect
select top-2 experts instead of 1, 3 or 4 (ablation)MoE-Fusion · FLIRfusion metricsImproved
set alpha above 10 instead of 10 (ablation)MoE-Fusion · FLIRfusion metricsMixed
set alpha below 10 instead of 10 (ablation)MoE-Fusion · FLIRfusion metricsHurt

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