Research map / Detection and segmentation / CNN features
OCCO: LVM-Guided Infrared and Visible Image Fusion Framework Based on Object-Aware and Contextual Contrastive Learning
Hui Li, Congcong Bian, Zeyang Zhang, Xiaoning Song, Xi Li, Xiao‐Jun Wu
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 |
|---|---|---|---|
| balance visible/infrared shared-information weights (0.5:0.5 instead of 1:0) (ablation) | OCCO · FMB | CC: 0.501 -> 0.634 | Improved |
| balance weights (0.5:0.5 instead of 0:1) (ablation) | OCCO · FMB | CC: 0.462 -> 0.634 | Improved |
| balance weights (0.5:0.5 instead of 0.2:0.8) (ablation) | OCCO · FMB | CC: 0.380 -> 0.634 | Improved |
| extreme weights 1:0 / 0:1 vs balanced on SF (ablation) | OCCO · FMB | SF: 16.000 (1:0) vs 15.095; 12.671 (0:1) | Mixed |
| contextual contrastive loss weight 10 instead of 0.1 (ablation) | OCCO · FMB | SF: 12.329 -> 15.095 | Improved |
| contextual contrastive loss weight 10 instead of 1 (ablation) | OCCO · FMB | SF: 13.580 -> 15.095 | Improved |
| contextual contrastive loss weight 10 instead of 100 (ablation) | OCCO · FMB | SF: 13.314 -> 15.095 | Improved |
| OCCO vs CDDFuse on semantic segmentation | OCCO · MSRS segmentation | mIoU: 62.224 -> 63.72 | Improved |
| fused image vs visible-only input for segmentation | OCCO · MSRS segmentation | mIoU: 58.623 -> 63.72 | Improved |
| OCCO vs best other method on MSRS detection | OCCO · MSRS detection | mAP: 0.790 -> 0.803 | Improved |
| OCCO vs SegMif on M3FD detection | OCCO · M3FD detection | mAP: 0.6647 -> 0.6745 | Improved |
| OCCO vs CDDFuse on FMB fusion entropy | OCCO · FMB | EN: 6.778 -> 7.035 | Improved |
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.
- CDDFuse — CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion (CVPR 2023) · better on 3 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
- LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images (TPAMI 2023 · similarity 0.86)
- CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion (IJCV 2023 · similarity 0.86)
- Image Fusion via Vision-Language Model (ICML 2024 · similarity 0.85)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.83)
- MRFS: Mutually Reinforcing Image Fusion and Segmentation (CVPR 2024 · similarity 0.83)
- OGP-Net: Optical Guidance Meets Pixel-Level Contrastive Distillation for Robust Multi-Modal and Missing Modality Segmentation (AAAI 2025 · similarity 0.83)
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.
