Research map / Vision-language and multimodal / Cross-modal learning
Delivering Arbitrary-Modal Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Depth, Event, and LiDAR successively to RGB | CMNeXt · DeLiVER | mIoU: 57.20%→63.58%→64.44%→66.30% | Helped |
| Add AoLP, DoLP, and NIR successively | CMNeXt · MCubeS | mIoU: 33.70 -> 48.42 -> 49.48 -> 51.54 | Helped |
| Add 80 supplementary light-field views rather than 33 | CMNeXt · UrbanLF-Real | mIoU: 82.62 -> 83.11 | Hurt |
| Add 80 supplementary light-field views rather than 33 | CMNeXt · UrbanLF-Syn | mIoU: 80.98 -> 81.02 | Helped |
| Add the addition operation for supplementary modalities (ablation) | CMNeXt · DeLiVER | mIoU: 64.56 -> 66.30 | Helped |
| Add SQ-Hub to select complementary features (ablation) | CMNeXt · DeLiVER | mIoU: 64.41 -> 66.30 | Helped |
| Use PPX instead of MSCA (ablation) | CMNeXt · DeLiVER | mIoU: 63.94 -> 66.30 | Helped |
| Add SE channel processing to PPX (ablation) | CMNeXt · DeLiVER | mIoU: 63.27 -> 66.30 | Helped |
| Add FRM (ablation) | CMNeXt · DeLiVER | mIoU: 62.71 -> 66.30 | Helped |
| Add FRM and FFM (ablation) | CMNeXt · DeLiVER | mIoU: 56.54 -> 66.30 | Helped |
Closest papers by meaning
- Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation (CVPR 2025 · similarity 0.89)
- How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation (ICML 2025 · similarity 0.87)
- OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation (NeurIPS 2025 · similarity 0.86)
- Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation (ICLR 2025 · similarity 0.86)
- PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation (AAAI 2025 · similarity 0.86)
- UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather (CVPR 2024 · 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.