← Search

Shunli Ren

2 accepted papers

2021

Learning Distilled Collaboration Graph for Multi-Agent Perception

NeurIPS 2021poster

To promote better performance-bandwidth trade-off for multi-agent perception, we propose a novel distilled collaboration graph (DiscoGraph) to model trainable, pose-aware, and adaptive collaboration among agents. Our key novelties lie in two aspects. First, we propose a teacher-student framework to…