Instance-Aware Knowledge Distillation for Semi-Supervised Learning of an On-Board Multi-Task Dense Prediction Model for Collision Avoidance System 文章

arXiv:2606.16414v1 Announce Type: new Abstract: Collision avoidance systems have evolved toward camera-based deep learning approaches for driving scene understanding. However, deployment in edge environments such as country clubs is constrained by limited computational resources and unreliable communication infrastructure. Moreover, constructing large-scale datasets for the target domain involves substantial annotation cost. To address these limitations, we propose an instance-aware knowledge distillation framework for semi-supervised learning. Specifically, we generate pseudo labels that mitigate teacher bias by leveraging domain priors from the teacher and instance-centric knowledge from foundation models. The trained lightweight student is deployed in the proposed collision avoidance system and performs multiple dense prediction tasks in real-time.