Research map / Vision-language and multimodal / Cross-modal learning
$\ell _{0}$ℓ0-Regularized Sparse Coding-Based Interpretable Network for Multi-Modal Image Fusion
Gargi Panda, Soumitra Kundu, Saumik Bhattacharya, Aurobinda Routray
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 |
|---|---|---|---|
| use FNet fused images instead of visible-only input | YOLO-style detector · M3FD object detection | mAP@[0.5:0.95] average: 0.600 -> 0.620 | Improved |
| use FNet fused images instead of visible-only input | segmentation network · MFNet semantic segmentation | mIoU average: 0.724 -> 0.780 | Improved |
| use FNet fused images instead of CDDFuse | downstream segmenter · MFNet semantic segmentation | mIoU average: 0.748 -> 0.780 | Improved |
| use FNet instead of SwinFusion | fusion network · FLOPs on 320x320 pairs | FLOPs (G): 117.53 -> 0.33 | Improved |
| use FNet instead of CDDFuse | fusion network · FLOPs on 320x320 pairs | FLOPs (G): 184.56 -> 0.33 | Improved |
| use FNet instead of SwinFusion | fusion network · Harvard CT-MRI | VIF: 0.56 -> 0.57 | Improved |
| use FNet instead of CDDFuse | fusion network · Harvard PET-MRI | VIF: 0.63 -> 0.71 | Improved |
| use FNet instead of CDDFuse | fusion network · KAIST (VIS-IR) | VIF: 0.86 -> 0.84 | Hurt |
| use FNet instead of CDDFuse | fusion network · RGB-NIR Scene (VIS-NIR) | MI: 2.28 -> 2.09 | Hurt |
| use FNet instead of SwinFusion | fusion network · Harvard PET-MRI | CE: 0.78 -> 0.78 | Hurt |
| apply sigmoidal thresholding in last iteration module of LZSC block (u1 branch) | FNet LZSC block · TNO feature histograms | null features count: increase by 84.4% | Improved |
| apply sigmoidal thresholding in last iteration module of LZSC block (c branch) | FNet LZSC block · TNO feature histograms | null features count: increase by 1068.8% | Improved |
Closest papers by meaning
- SMR-Net: Semantic-Guided Mutually Reinforcing Network for Cross-Modal Image Fusion and Salient Object Detection (AAAI 2025 · similarity 0.88)
- CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion (CVPR 2023 · similarity 0.87)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.85)
- Multi-Modal Object Re-identification via Sparse Mixture-of-Experts (ICML 2025 · similarity 0.85)
- Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion (NeurIPS 2026 · similarity 0.85)
- When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion (NeurIPS 2026 · 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.
