CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception
CauseCollab is proposed, a causal unified and modality-agnostic network that formulates representation learning in the protocol space from a causal perspective, explicitly disentangling semantic factors from modality-specific statistical confounders via causal metric learning.
Wei-Ze Li, Yang Li, Quan Yuan et al.
· 0 citations