Deep learning-based models are at the forefront of most driver observation
benchmarks due to their remarkable accuracies but are also associated with high
computational costs. This is challenging, as resources are often limited in
real-world driving scenarios. This paper introduces a lightweight framework for
resource-efficient driver activity recognition. The framework enhances 3D
MobileNet, a neural architecture optimized for speed in video classification,
by incorporating knowledge distillation and model quantization to balance model
accuracy and computational efficiency. Knowledge distillation helps maintain
accuracy while reducing the model size by leveraging soft labels from a larger
teacher model (I3D), instead of relying solely on original ground truth data.
Model quantization significantly lowers memory and computation demands by using
lower precision integers for model weights and activations. Extensive testing
on a public dataset for in-vehicle monitoring during autonomous driving
demonstrates that this new framework achieves a threefold reduction in model
size and a 1.4-fold improvement in inference time, compared to an already
optimized architecture. The code for this study is available at
this https URL

通过使用知识蒸馏和模型量化来增强 3D MobileNet，该论文介绍了一个轻量级的资源高效驾驶员活动识别框架，通过从较大的教师模型（I3D）获取软标签来降低模型大小，降低内存和计算需求，从而实现模型大小的减小三倍和推断时间提升 1.4 倍。