CUEING: a lightweight model to Capture hUman attEntion In driviNG

TL;DR

This paper introduces CUEING, a lightweight, robust gaze prediction model for autonomous driving that improves accuracy and generalizability while drastically reducing computational complexity, facilitating in-vehicle deployment.

Contribution

The paper presents a novel adaptive dataset cleansing method and a lightweight convolutional self-attention model for human gaze prediction in driving scenarios.

Findings

Performance improved by up to 12.13%

Model complexity reduced by up to 98.2%

Enhanced generalizability across diverse scenarios

Abstract

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.