Research map / Vision-language and multimodal / Cross-modal learning
CoCoNet: Coupled Contrastive Learning Network with Multi-level Feature Ensemble for Multi-modality Image Fusion
Jinyuan Liu, Runjia Lin, Guanyao Wu, Risheng Liu, Zhongxuan Luo, Xin Fan
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 pretrained VGG features to the MAM (ablation) | CoCoNet · TNO | EN: 6.564 -> 6.786 | Improved |
| add channel attention to the MAM (ablation) | CoCoNet · TNO | SD: 9.511 -> 10.591 | Improved |
| add channel attention (without VGG) (ablation) | CoCoNet · TNO | VIF: 0.705 -> 0.774 | Improved |
| add VGG features and channel attention together (ablation) | CoCoNet · TNO | EN: 6.564 -> 7.776 | Improved |
| add VGG features on top of channel attention (ablation) | CoCoNet · RoadScene | EN: 7.288 -> 7.693 | Improved |
| add low-level VGG features (ablation) | CoCoNet · TNO | EN: 6.796 -> 7.776 | Improved |
| add middle-level VGG features (ablation) | CoCoNet · TNO | EN: 7.338 -> 7.776 | Improved |
| add high-level VGG features (ablation) | CoCoNet · TNO | EN: 7.294 -> 7.776 | Improved |
| add middle/high-level features to low-level only (ablation) | CoCoNet · TNO | EN: 7.387 -> 7.776 | Improved |
| use full multi-level features instead of low-level only (ablation) | CoCoNet · RoadScene | VIF: 0.768 -> 0.854 | Improved |
| add channel attention (ablation) | CoCoNet · TNO | SCD: 1.736 -> 1.681 | Hurt |
| use target and detail contrastive regularization with corresponding samples (ablation) | CoCoNet · TNO | visual quality | Improved |
Closest papers by meaning
- LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images (TPAMI 2023 · similarity 0.88)
- Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion (AAAI 2024 · similarity 0.85)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.85)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.84)
- Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion (ICML 2025 · similarity 0.84)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 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.
