Research map / Vision-language and multimodal / Cross-modal learning
Difference-Aware Decision Learning for Multimodal Image Fusion
Hao Pan, Jian Dai, Yuan Sun, Zhenwen Ren, Xingfeng Li
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add MDA and CDG decision modules (ablation) | IDEAL · MSRS | SD: 46.00 -> 50.93 | Improved |
| add MDA and CDG decision modules (ablation) | IDEAL · M3FD | SD: 30.98 -> 40.31 | Improved |
| add Modal Difference Attention (MDA) module (ablation) | IDEAL · M3FD | SD: 34.56 -> 40.31 | Improved |
| add gradient fidelity risk (ablation) | IDEAL · M3FD | SCD: 1.05 -> 1.52 | Improved |
| add gradient fidelity risk (ablation) | IDEAL · MSRS | SF: 10.81 -> 12.62 | Improved |
| add pixel intensity risk (ablation) | IDEAL · M3FD | SD: 35.93 -> 40.31 | Improved |
| add pixel intensity risk (ablation) | IDEAL · FMB | SCD: 1.62 -> 1.63 | No clear effect |
| use observation-conditioned decisions vs strongest SCD baseline | IDEAL · M3FD | SCD: 1.7170 -> 1.5238 | Hurt |
| use IDEAL fusion as input to detector | IDEAL · MSRS detection | mAP@[0.5:0.95]: 66.9 -> 67.5 | Improved |
| use IDEAL fusion for detection mAP@0.5 | IDEAL · MSRS detection | mAP@0.5: 93.3 -> 93.0 | No clear effect |
| compare IDEAL vs CDDFuse efficiency | IDEAL · MSRS | GFLOPs: 220.92 -> 1.00 | Improved |
| compare IDEAL vs GIFNet on FMB average gradient | IDEAL · FMB | AG: 4.9269 -> 4.7895 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EMMA — EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment (ICLR 2025) · better on 5 of 5 shared results
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
- Provable Dynamic Fusion for Low-Quality Multimodal Data (ICML 2023 · similarity 0.88)
- Predictive Dynamic Fusion (ICML 2024 · similarity 0.88)
- When to Align, When to Predict: A Phase Diagram for Multimodal Learning (NeurIPS 2026 · similarity 0.86)
- Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning (NeurIPS 2025 · similarity 0.86)
- Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion (CVPR 2024 · similarity 0.85)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.85)
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.
