Enhancing Cross-Dataset Performance of Distracted Driving Detection With Score Softmax Classifier And Dynamic Gaussian Smoothing Supervision

TL;DR

This paper introduces a Score-Softmax classifier with dynamic Gaussian smoothing supervision to improve cross-dataset driver distraction detection, significantly enhancing robustness and accuracy across multiple datasets.

Contribution

It proposes a novel Score-Softmax classifier combined with dynamic Gaussian smoothing supervision to reduce overconfidence and improve cross-dataset performance in driver behavior recognition.

Findings

Cross-dataset accuracy improved by up to 21.34%.

Model robustness increased by reducing background noise interference.

The method achieves better generalization without changing the model architecture.

Abstract

Deep neural networks enable real-time monitoring of in-vehicle drivers, facilitating the timely prediction of distractions, fatigue, and potential hazards. This technology is now integral to intelligent transportation systems. Recent research has exposed unreliable cross-dataset driver behavior recognition due to a limited number of data samples and background noise. In this paper, we propose a Score-Softmax classifier, which reduces the model overconfidence by enhancing category independence. Imitating the human scoring process, we designed a two-dimensional dynamic supervisory matrix consisting of one-dimensional Gaussian-smoothed labels. The dynamic loss descent direction and Gaussian smoothing increase the uncertainty of training to prevent the model from falling into noise traps. Furthermore, we introduce a simple and convenient multi-channel information fusion method;it addresses the fusion issue among arbitrary Score-Softmax classification heads. We conducted cross-dataset experiments using the SFDDD, AUCDD, and the 100-Driver datasets, demonstrating that Score-Softmax improves cross-dataset performance without modifying the model architecture. The experiments indicate that the Score-Softmax classifier reduces the interference of background noise, enhancing the robustness of the model. It increases the cross-dataset accuracy by 21.34%, 11.89%, and 18.77% on the three datasets, respectively. The code is publicly available at https://github.com/congduan-HNU/SSoftmax.