Preprint
Aug 2026
CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation
This work proposes a robust Collaborative perception framework with expert-driven Detection and bev Segmentation (CoDS) and designs the Semantic Mixture-of-Experts (S-MoE) module to extract differentiated features for inconsistent feature demands.
Jinlong Wang, Yuang Jia, Jun-Hong Lin et al.
· 0 citations