Research map / Vision-language and multimodal / Cross-modal learning
X-MoGe: A Cross-Modal Adaptation Framework with Mixture-of-Experts and Geometry Guidance for Heterogeneous Collaborative Perception
Wenkai Lin, Zhihong Liu, Chenglu Wen
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 the P-MoE adaptor (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.5: 65.28 -> 68.15 | Improved |
| add the P-MoE adaptor (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.7: 51.11 -> 54.93 | Improved |
| add SGE (Sobel gradient encoding) (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.5: 66.78 -> 68.15 | Improved |
| add SGE (Sobel gradient encoding) (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.7: 52.11 -> 54.93 | Improved |
| add EAE (edge-aware enhancement) (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.7: 53.61 -> 54.93 | Improved |
| add EAE (edge-aware enhancement) (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.5: 66.57 -> 68.15 | Improved |
| add UA-head (uncertainty-aware head) (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.5: 67.38 -> 68.15 | Improved |
| add UA-head (uncertainty-aware head) (ablation) | X-MoGe · DAIR-V2X pp4-res50 | AP@0.7: 54.36 -> 54.93 | Improved |
| use P-MoE adaptor instead of PnPDA | F-Cooper fusion · OPV2V pp8-res50 | AP@0.7: 56.88 -> 57.01 | Improved |
| use P-MoE adaptor instead of PnPDA | F-Cooper fusion · OPV2V pp8-eff | AP@0.7: 55.13 -> 56.50 | Improved |
| use P-MoE adaptor instead of PnPDA | CoBEVT fusion · OPV2V pp8-eff | AP@0.7: 53.18 -> 59.16 | Improved |
| use X-MoGe instead of strongest baseline | OPV2V 3 agents · pp8-res50-vn4 | AP@0.7: +4.15 AP | Improved |
Closest papers by meaning
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.90)
- One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception (CVPR 2025 · similarity 0.89)
- STAMP: Scalable Task- And Model-agnostic Collaborative Perception (ICLR 2025 · similarity 0.87)
- CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization (CVPR 2025 · similarity 0.87)
- Privacy-Preserving V2X Collaborative Perception Integrating Unknown Collaborators (AAAI 2025 · similarity 0.87)
- CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning (AAAI 2025 · similarity 0.87)
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.
