Interpretable Self-Attention Temporal Reasoning for Driving Behavior Understanding
This addresses the need for interpretable and accurate driving behavior prediction for autonomous driving systems, but is incremental as it builds on existing 3D CNNs.
The paper tackled the problem of 3D CNNs failing to capture causal reasoning for driving behavior classification, and by introducing a Temporal Reasoning Block, achieved 86.3% accuracy, outperforming state-of-the-art models.
Performing driving behaviors based on causal reasoning is essential to ensure driving safety. In this work, we investigated how state-of-the-art 3D Convolutional Neural Networks (CNNs) perform on classifying driving behaviors based on causal reasoning. We proposed a perturbation-based visual explanation method to inspect the models' performance visually. By examining the video attention saliency, we found that existing models could not precisely capture the causes (e.g., traffic light) of the specific action (e.g., stopping). Therefore, the Temporal Reasoning Block (TRB) was proposed and introduced to the models. With the TRB models, we achieved the accuracy of $\mathbf{86.3\%}$, which outperform the state-of-the-art 3D CNNs from previous works. The attention saliency also demonstrated that TRB helped models focus on the causes more precisely. With both numerical and visual evaluations, we concluded that our proposed TRB models were able to provide accurate driving behavior prediction by learning the causal reasoning of the behaviors.