Enhancing Lightweight Face Information Detection Network with Multi-Clue Interaction and Part-Aware Supervision

Jing-Hong Liu, Yi Chen, Zer-Wei Lee, Chih-Yuan Hsu, Yu-Lun Yen, Pei-Yung Hsiao, Li-Chen Fu

Abstract: In recent years, technologies related to intelligent vehicles have seen rapid development, making the design of driver monitoring systems that can operate on vehicles a critical area of focus. These systems analyze drivers' facial information to assess their attention status and ability to control the vehicle. In this paper, we propose a lightweight, multitask deep learning model for detecting head pose, gaze direction, and eye state from facial images. This model is specifically designed for integration into driver monitoring systems, aiming to determine whether the driver is focused on the road. To facilitate deployment on embedded vehicle devices, our approach leverages multitask learning with carefully designed task branches to create an efficient and lightweight system. Each task is supported by dedicated branches to ensure the extraction of necessary features, with part-aware supervision enhancing the focus on relevant facial regions. Additionally, clue features encode part-specific implicit knowledge, improving task-specific feature initialization and overall model performance. We evaluate our model using the AFLW2000, BIWI, Gaze360, and CEW datasets, demonstrating that our method achieves competitive performance with reduced parameter costs. Our results show superior performance under lightweight conditions compared to existing methods, demonstrating the effectiveness of our approach in real-world applications.