Gated Driver Attention Predictor

TL;DR

This paper introduces Gate-DAP, a flexible network connection gating mechanism for driver attention prediction that improves accuracy across diverse driving scenarios by selectively integrating spatial, temporal, and modality information.

Contribution

The paper proposes a novel, modular gating architecture for driver attention prediction, enhancing interpretability and performance over existing methods.

Findings

Outperforms state-of-the-art methods on DADA-2000 and BDDA datasets.

Flexible plug-and-play gating modules improve prediction accuracy.

Demonstrates robustness across various road types and weather conditions.

Abstract

Driver attention prediction implies the intention understanding of where the driver intends to go and what object the driver concerned about, which commonly provides a driving task-guided traffic scene understanding. Some recent works explore driver attention prediction in critical or accident scenarios and find a positive role in helping accident prediction, while the promotion ability is constrained by the prediction accuracy of driver attention maps. In this work, we explore the network connection gating mechanism for driver attention prediction (Gate-DAP). Gate-DAP aims to learn the importance of different spatial, temporal, and modality information in driving scenarios with various road types, occasions, and light and weather conditions. The network connection gating in Gate-DAP consists of a spatial encoding network gating, long-short-term memory network gating, and information type gating modules. Each connection gating operation is plug-and-play and can be flexibly assembled, which makes the architecture of Gate-DAP transparent for evaluating different spatial, temporal, and information types for driver attention prediction. Evaluations on DADA-2000 and BDDA datasets verify the superiority of the proposed method with the comparison with state-of-the-art approaches. The code is available on https://github.com/JWFangit/Gate-DAP.