DAMap: Distance-aware MapNet for High Quality HD Map Construction

TL;DR

DAMap introduces a novel approach for high-quality HD map construction in autonomous driving by addressing task misalignment issues with specialized loss functions and attention mechanisms, leading to improved performance on key benchmarks.

Contribution

The paper proposes DAMap, a new method with Distance-aware Focal Loss, Task Modulated Deformable Attention, and a Hybrid Loss Scheme to enhance HD map prediction accuracy.

Findings

Consistent performance improvements on NuScenes and Argoverse2 benchmarks.

Effective handling of one-to-many matching issues in HD map prediction.

Robustness across different metrics, backbones, and training schedules.

Abstract

Predicting High-definition (HD) map elements with high quality (high classification and localization scores) is crucial to the safety of autonomous driving vehicles. However, current methods perform poorly in high quality predictions due to inherent task misalignment. Two main factors are responsible for misalignment: 1) inappropriate task labels due to one-to-many matching queries sharing the same labels, and 2) sub-optimal task features due to task-shared sampling mechanism. In this paper, we reveal two inherent defects in current methods and develop a novel HD map construction method named DAMap to address these problems. Specifically, DAMap consists of three components: Distance-aware Focal Loss (DAFL), Hybrid Loss Scheme (HLS), and Task Modulated Deformable Attention (TMDA). The DAFL is introduced to assign appropriate classification labels for one-to-many matching samples. The TMDA is proposed to obtain discriminative task-specific features. Furthermore, the HLS is proposed to better utilize the advantages of the DAFL. We perform extensive experiments and consistently achieve performance improvement on the NuScenes and Argoverse2 benchmarks under different metrics, baselines, splits, backbones, and schedules. Code will be available at https://github.com/jpdong-xjtu/DAMap.