Research map / Multi-agent systems and games / Cooperative multi-agent RL
mmCooper: A Multi-agent Multi-stage Communication-efficient and Collaboration-robust Cooperative Perception Framework
Bingyi Liu, Jian Teng, Hongfei Xue, Enshu Wang, Chuanhui Zhu, Pu Wang, Libing 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 |
|---|---|---|---|
| add Confidence-based Filter Generation (CFG) module (ablation) | mmCooper · OPV2V | AP@0.7: 73.46 -> 78.11 | Improved |
| add CFG module (ablation) | mmCooper · DAIR-V2X | AP@0.7: 47.66 -> 48.27 | Improved |
| add CFG module (ablation) | mmCooper · V2XSet | AP@0.7: 62.78 -> 65.86 | Improved |
| add Multi-scale Offset-aware Fusion (MOF) (ablation) | mmCooper · OPV2V | AP@0.7: 72.60 -> 78.11 | Improved |
| add MOF (ablation) | mmCooper · V2XSet | AP@0.7: 64.33 -> 65.86 | Improved |
| add BBox Filtering & Calibration (BFC) (ablation) | mmCooper · OPV2V | AP@0.7: 76.77 -> 78.11 | Improved |
| add BFC (ablation) | mmCooper · DAIR-V2X | AP@0.7: 44.31 -> 48.27 | Improved |
| add late-stage fusion to intermediate fusion (multi-stage) (ablation) | mmCooper · OPV2V | AP@0.7: 76.83 -> 78.11 | Improved |
| add intermediate-stage fusion to late fusion (multi-stage) (ablation) | mmCooper · OPV2V | AP@0.7: 66.80 -> 78.11 | Improved |
| add intermediate-stage fusion to late fusion (multi-stage) (ablation) | mmCooper · V2XSet | AP@0.7: 54.36 -> 65.86 | Improved |
| use Deformable BBox Attention instead of standard cross-attention (ablation) | mmCooper · OPV2V | AP@0.7: 74.04 -> 78.11 | Improved |
| use Deformable BBox Attention instead of standard cross-attention (ablation) | mmCooper · DAIR-V2X | AP@0.7: 47.69 -> 48.27 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- ERMVP — ERMVP: Communication-Efficient and Collaboration-Robust Multi-Vehicle Perception in Challenging Environments (CVPR 2024) · better on 4 of 4 shared results
- Where2comm — Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps (NeurIPS 2022) · better on 4 of 4 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
- CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization (CVPR 2025 · similarity 0.92)
- Multi-agent Collaborative Perception via Motion-aware Robust Communication Network (CVPR 2024 · similarity 0.89)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.88)
- CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning (AAAI 2025 · similarity 0.88)
- STAMP: Scalable Task- And Model-agnostic Collaborative Perception (ICLR 2025 · similarity 0.88)
- RCP-Bench: Benchmarking Robustness for Collaborative Perception Under Diverse Corruptions (CVPR 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.
