BriefGPT.xyz
Aug, 2022
功能匹配在驾驶场景识别中的有效性
Effectiveness of Function Matching in Driving Scene Recognition
HTML
PDF
Shingo Yashima
TL;DR
本研究通过大量的无标签数据来进行知识蒸馏,以提高自动驾驶结构预测任务的紧凑学生模型的性能,并通过实验表明,通过这种方法可以大大提高紧凑学生模型的性能,甚至与大规模教师模型的性能相匹配。
Abstract
knowledge distillation
is an effective approach for training compact recognizers required in
autonomous driving
. Recent studies on image classification have shown that matching student and teacher on a wide range
→