Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer
Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer
复制标题
DOI：
10.1109/tits.2022.3217342
复制
发表时间：
2023-01
影响因子：
8.5
通讯作者：
Dichao Liu;T. Yamasaki;Yu Wang;K. Mase;Jien Kato
中科院分区：
文献类型：
--
作者：
Dichao Liu;T. Yamasaki;Yu Wang;K. Mase;Jien Kato
近年来，世界范围内的交通事故数量不断增加。许多事故都是由分心的司机造成的，他们把注意力从驾驶上移开。受卷积神经网络（CNN）在计算机视觉中的成功启发，许多研究人员开发了基于CNN的算法来识别仪表盘摄像头的分心驾驶，并警告驾驶员不要采取不安全的行为。然而，目前的模型参数太多，这是不可行的车载计算。这项工作提出了一种新的知识蒸馏为基础的框架来解决这个问题。所提出的框架首先通过逐步加强CNN从浅层到深层对光照变化的鲁棒性来构建高性能教师网络。然后，教师网络被用来指导学生网络的架构搜索过程中，通过知识蒸馏。之后，我们再次使用教师网络，通过知识蒸馏将知识传递到学生网络。在Statefarm分心驾驶员检测数据集和AUC分心驾驶员数据集上的实验结果表明，所提出的方法对于从照片中识别分心驾驶行为非常有效：（i）教师网络的准确率超过了以前的最佳准确率;（ii）学生网络仅用0.42M参数就达到了非常高的准确率（约为以前最轻量级模型的55%）。此外，学生网络架构可以扩展到时空3D CNN，用于从视频剪辑中识别分心驾驶。3D学生网络在很大程度上超过了之前的最佳精度，在Drive&Act数据集上只有203万个参数。源代码可在https://github.com/Dichao-Liu/Lightweight_Distracted_Driver_Recognition_with_Distillation-Based_NAS_and_Knowledge_Transfer上获取
The number of traffic accidents has been continuously increasing in recent years worldwide. Many accidents are caused by distracted drivers, who take their attention away from driving. Motivated by the success of Convolutional Neural Networks (CNNs) in computer vision, many researchers developed CNN-based algorithms to recognize distracted driving from a dashcam and warn the driver against unsafe behaviors. However, current models have too many parameters, which is unfeasible for vehicle-mounted computing. This work proposes a novel knowledge-distillation-based framework to solve this problem. The proposed framework first constructs a high-performance teacher network by progressively strengthening the robustness to illumination changes from shallow to deep layers of a CNN. Then, the teacher network is used to guide the architecture searching process of a student network through knowledge distillation. After that, we use the teacher network again to transfer knowledge to the student network by knowledge distillation. Experimental results on the Statefarm Distracted Driver Detection Dataset and AUC Distracted Driver Dataset show that the proposed approach is highly effective for recognizing distracted driving behaviors from photos: (i) the teacher network’s accuracy surpasses the previous best accuracy; (ii) the student network achieves very high accuracy with only 0.42M parameters (around 55% of the previous most lightweight model). Furthermore, the student network architecture can be extended to a spatial-temporal 3D CNN for recognizing distracted driving from video clips. The 3D student network largely surpasses the previous best accuracy with only 2.03M parameters on the Drive&Act Dataset. The source code is available at https://github.com/Dichao-Liu/Lightweight_Distracted_Driver_Recognition_with_Distillation-Based_NAS_and_Knowledge_Transfer