Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learning Distilled Collaboration Graph for Multi-Agent Perception
Yiming Li, Shunli Ren, Pengxiang Wu, Siheng Chen, Chen Feng, Wenjun Zhang
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 knowledge distillation on post-collaboration feature maps from early-collaboration teacher (ablation) | DiscoGraph · V2X-Sim 1.0 | AP@IoU=0.5: 57.2 -> 60.3 | Improved |
| add knowledge distillation (ablation) | DiscoGraph · V2X-Sim 1.0 | AP@IoU=0.7: 52.3 -> 53.9 | Improved |
| add KD to Max aggregation (ablation) | Max · V2X-Sim 1.0 | AP@IoU=0.5: 56.7 -> 56.7 | No clear effect |
| add KD to Sum aggregation (ablation) | Sum · V2X-Sim 1.0 | AP@IoU=0.7: 50.9 -> 46.3 | Hurt |
| add KD to Cat aggregation (ablation) | Cat · V2X-Sim 1.0 | AP@IoU=0.5: 55.0 -> 57.5 | Improved |
| use matrix-valued edge weight instead of scalar weighted average (both with KD) (ablation) | DiscoGraph · V2X-Sim 1.0 | AP@IoU=0.5: 56.7 -> 60.3 | Improved |
| use matrix-valued edge weight instead of scalar weighted average (no KD) (ablation) | DiscoGraph · V2X-Sim 1.0 | AP@IoU=0.5: 56.1 -> 57.2 | Improved |
| apply KD on more decoder layers: M{1,2,3} vs only H (ablation) | DiscoNet · V2X-Sim 1.0 | AP@IoU=0.5: 57.5 -> 60.3 | Improved |
| add KD on fourth decoder layer M{4} (ablation) | DiscoNet · V2X-Sim 1.0 | AP@IoU=0.5: 60.3 -> 59.1 | Hurt |
| drop KD on H while keeping KD on M{1-4} (ablation) | DiscoNet · V2X-Sim 1.0 | AP@IoU=0.5: 59.1 -> 58.3 | Hurt |
| apply late collaboration to upper bound | Upper-bound · V2X-Sim 1.0 | AP@IoU=0.5: 63.3 -> 59.7 | Hurt |
| apply late collaboration to lower bound | Lower-bound · V2X-Sim 1.0 | AP@IoU=0.5: 45.8 -> 57.6 | Improved |
Closest papers by meaning
- An Extensible Framework for Open Heterogeneous Collaborative Perception (ICLR 2024 · similarity 0.88)
- What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception (AAAI 2024 · similarity 0.88)
- NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception (NeurIPS 2025 · similarity 0.87)
- CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-Tuning (AAAI 2025 · similarity 0.87)
- Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism (NeurIPS 2025 · similarity 0.86)
- Scaling Large Language Model-based Multi-Agent Collaboration (ICLR 2025 · 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.
