A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration
This work revisits multi-modal fusion from the perspective of socialized learning and proposes adapter to DINOv3 (A2DINOv3), a multi-expert collaboration framework with a Socialized Collaboration Protocol (SCP), where RGB and infrared branches are modeled as heterogeneous experts that independently preserve their speci...
Jiekang Feng, Zhi-He Fan, Yun-Qi Zhu et al.
· 0 citations