Research map / Multi-agent systems and games / Human-AI and goal-conditioned
UECP: Uncertainty-Enhanced Collaborative Perception
Kang Yang, Tianci Bu, Peng Wang, Deying Li, Jie Wen, Yongcai Wang
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 uncertainty map (UM) (ablation) | F-Cooper-like baseline · DAIR-V2X val | AP@70: 54.65 -> 56.92 | Improved |
| add multi-scale pyramid (MS) (ablation) | baseline + UM · DAIR-V2X val | AP@70: 56.92 -> 59.74 | Improved |
| add UWD (ablation) | baseline + UM + MS · DAIR-V2X val | AP@70: 59.74 -> 60.63 | Improved |
| add UGRF (ablation) | baseline + UM + MS + UWD · DAIR-V2X val | AP@70: 60.63 -> 61.12 | Improved |
| use pyramid scales (4,2,1) instead of single scale (ablation) | UECP · DAIR-V2X val | AP@70: 59.03 -> 61.12 | Improved |
| use scales (4,2,1) instead of (2,1) (ablation) | UECP · DAIR-V2X val | AP@70: 59.79 -> 61.12 | Improved |
| use uncertainty map instead of confidence map (ablation) | UECP · DAIR-V2X val | AP@70: 56.47 -> 61.12 | Improved |
| add confidence map guidance over no map (ablation) | UECP · DAIR-V2X val | AP@70: 55.91 -> 56.47 | Improved |
| use sum fusion instead of max (ablation) | UECP · DAIR-V2X val | AP@70: 59.86 -> 61.12 | Improved |
| use sum fusion instead of mean (ablation) | UECP · DAIR-V2X val | AP@70: 57.66 -> 61.12 | Improved |
| use learned uncertainty instead of density-direct map (ablation) | UECP · DAIR-V2X val | AP@70: 60.77 -> 61.12 | Improved |
| replace confidence map with uncertainty map | HEAL · DAIR-V2X val | AP@70: 55.56 -> 58.93 | Improved |
Closest papers by meaning
- RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (CVPR 2025 · similarity 0.89)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.87)
- CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization (CVPR 2025 · similarity 0.86)
- AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning (AAAI 2026 · similarity 0.86)
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios (NeurIPS 2025 · similarity 0.85)
- ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments (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.
