解决高精地图生成中分类定位不准的问题，提升自动驾驶安全
DAMap: Distance-aware MapNet for High Quality HD Map Construction
- 引入距离感知焦点损失，优化一对多匹配样本的标签分配
- 在NuScenes和Argoverse2上显著提升分类与定位精度
- 适合需要高精度地图的自动驾驶系统研发人员参考
高质量的高精地图元素预测对自动驾驶车辆的安全至关重要。然而，现有方法因任务错位导致性能不佳。主要问题有两个：一是因一对多匹配查询共享相同标签而产生不合适的任务标签；二是任务共享采样机制导致特征不优。本文揭示了这两个固有缺陷，并提出新型高精地图构建方法DAMap。该方法包含三个组件：距离感知焦点损失（DAFL）、混合损失方案（HLS）和任务调制可变形注意力（TMDA）。DAFL用于为一对多匹配样本分配合理标签，TMDA用于获取具有区分性的任务特定特征，HLS则更好地发挥DAFL的优势。在NuScenes和Argoverse2基准上，不同指标、基线、数据划分、主干网络和训练策略下均取得一致性能提升。代码将发布于https://github.com/jpdong-xjtu/DAMap。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。