Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation

arXiv:2606.25278v1 Announce Type: new Abstract: Multi-modal fusion and multi-model ensembling are prevalent in enhancing the performance of 3D semantic segmentation. Despite the impressive performance, these methods either rely on auxiliary input signals or suffer from costly computational expense. To efficaciously enhance the segmentation performance without introducing intolerable costs, we propose to transfer the rich knowledge from the multi-modal model (i.e., point clouds and images) and mu...