CUEING: a lightweight model to Capture hUman attEntion In driviNG
This work addresses the need for efficient gaze predictors to enhance trust in autonomous vehicles, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of predicting human gaze in driving to improve autonomous driving systems by proposing a noise-cleansing technique and a lightweight model, resulting in up to 12.13% performance improvement and 98.2% reduction in model complexity.
Discrepancies in decision-making between Autonomous Driving Systems (ADS) and human drivers underscore the need for intuitive human gaze predictors to bridge this gap, thereby improving user trust and experience. Existing gaze datasets, despite their value, suffer from noise that hampers effective training. Furthermore, current gaze prediction models exhibit inconsistency across diverse scenarios and demand substantial computational resources, restricting their on-board deployment in autonomous vehicles. We propose a novel adaptive cleansing technique for purging noise from existing gaze datasets, coupled with a robust, lightweight convolutional self-attention gaze prediction model. Our approach not only significantly enhances model generalizability and performance by up to 12.13% but also ensures a remarkable reduction in model complexity by up to 98.2% compared to the state-of-the art, making in-vehicle deployment feasible to augment ADS decision visualization and performance.