LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving

arXiv:2403.08215v1 Announce Type: cross
Abstract: Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric prior knowledge acquired by a duplex-encoder teacher model into a single-encoder student model is a practical, albeit less explored research avenue. This paper delves into this topic and resorts to knowledge distillation approaches to address this problem. We introduce the Learning to Infuse "X" (LIX) …

abstract acquired arxiv autonomous autonomous driving become cs.ai cs.cv cs.lg cs.ro data data-fusion driving encoder fusion knowledge networks performance prior segmentation semantic spatial type visual