A Dynamic Multi-Level Feature Alignment Method for Domain Adaptive Driver Distraction Detection
- 13 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (1) , 1279-1294
Abstract
The use of smartphones and in-vehicle infotainment systems has made distracted driving a major cause of traffic accidents. Image-based models are essential for advanced driver assistance systems (ADAS) to detect distractions and alert drivers. However, a major challenge is the poor generalization of image-based detection models, particularly in cross-domain scenarios. Given the variability of real-world driving environments, it is essential to develop a model that performs consistently and efficiently across diverse conditions. In real world, due to the differences between the training scenarios (i.e., source domain) and the application scenarios (i.e., target domain), relying solely on either local alignment or global alignment cannot effectively address the various domain shift scenarios. Therefore, we propose DAF (Dynamic Adaptation Framework), a novel domain adaptation approach that automatically handles cross-domain shifts through dynamic feature alignment. Unlike conventional methods, DAF jointly optimizes global context preservation and local feature discrimination in a unified framework, continuously adapting to domain discrepancies through integrated representation learning. Experiments are conducted on three cross-domain driver distraction datasets including State-farm, AUC-Real, and AUC-Laboratory. The results demonstrate that the proposed method outperforms the compared methods, offering a potential choice for enhancing distraction detection performance in diverse scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (52072320)
- National Natural Science Foundation of China (52272421)
- State Key Laboratory of Intelligent Green Vehicle and Mobility (KFZ2409)
This publication has 81 references indexed in Scilit:
- Few-shot multi-domain text intent classification with Dynamic Balance Domain Adaptation Meta-learningExpert Systems with Applications, 2024
- Time-frequency supervised contrastive learning via pseudo-labeling: An unsupervised domain adaptation network for rolling bearing fault diagnosis under time-varying speedsAdvanced Engineering Informatics, 2023
- Disentanglement then reconstruction: Unsupervised domain adaptation by twice distribution alignmentsExpert Systems with Applications, 2023
- Multimodal driver distraction detection using dual-channel network of CNN and TransformerExpert Systems with Applications, 2023
- Detecting and recognizing driver distraction through various data modality using machine learning: A review, recent advances, simplified framework and open challenges (2014–2021)Engineering Applications of Artificial Intelligence, 2022
- Driver behavior detection via adaptive spatial attention mechanismAdvanced Engineering Informatics, 2021
- A contextual and temporal algorithm for driver drowsiness detectionAccident Analysis & Prevention, 2018
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation2016
- Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation2016
- The relative importance of local phase and local amplitude in patchwise image reconstructionBiological Cybernetics, 1991