AI Paper Atlas

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

Self-supervised Multiplex Consensus Mamba for General Image Fusion

Yingying Wang, Rongjin Zhuang, Hui Zheng, Xuanhua He, Ke Cao, Xiaotong Tu, Xinghao Ding

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 2 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
use Mamba instead of convolution (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.735 -> 0.991Improved
use Mamba instead of window attention (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.672 -> 0.991Improved
use Mamba instead of self attention (ablation)SMC-Mamba · MSRS (IVIF)inference time (ms): 1271.691 -> 288.545Improved
add MAFE module (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.803 -> 0.991Improved
add MCCM module (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.702 -> 0.991Improved
add feature- and pixel-level contrastive losses (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.925 -> 0.991Improved
add MCCM loss (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.906 -> 0.991Improved
add expert diversity loss (ablation)SMC-Mamba · MSRS (IVIF)MI: 3.601 -> 4.490Improved
add workload balancing loss (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.947 -> 0.991Improved
add cross-modal scanning (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.896 -> 0.991Improved
add spatial-channel scanning (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.936 -> 0.991Improved
add frequency-rotational scanning (ablation)SMC-Mamba · MSRS (IVIF)VIF: 0.963 -> 0.991Improved

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