基于深度学习的在线建图的失效模式：如何度量与解决
Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them
为在线建图模型提供了一套可复用的泛化诊断工具：用地理邻近与拓扑相似度划分评测子集，配合基于 Frechet 距离的逐元素重建统计量，无需调阈值即可分离「输入特征记忆」与「地图拓扑过拟合」两种失效模式；其 MST 多样性指标与对称覆盖度指标也可直接用于其他 BEV/建图数据集的分裂质量检查与训练集去冗余。
原文依据 We propose metrics based on evaluation subsets that control for geographical proximity and topological similarity between training and validation scenes.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于深度学习的在线建图已成为自动驾驶的基石，但这类模型往往难以泛化到熟悉环境之外。我们提出一个框架，通过解耦两种效应来识别并度量其背后的失效模式：对输入特征的记忆，以及对已知地图拓扑的过拟合。我们提出基于评测子集的指标，用以控制训练场景与验证场景之间的地理邻近性与拓扑相似性。我们引入基于 Frechet 距离的重建统计量，无需阈值调参即可刻画逐元素的形状保真度，并定义互补的失效模式分数：输入特征过拟合分数，量化地理线索消失时的性能下降；拓扑过拟合分数，度量场景在拓扑上变得新颖时的性能退化。除模型之外，我们还分析数据集偏置，并贡献拓扑感知的诊断工具：用于训练集的最小生成树（MST）多样性指标，以及用于量化各数据划分之间拓扑相似性的对称覆盖度指标。基于这些工具，我们提出一种基于 MST 的稀疏化策略，在缩减训练规模的同时降低冗余、改善平衡并提升性能。在 nuScenes 与 Argoverse 2 上对多个最优模型的实验给出了更可信的泛化评估，并表明拓扑多样且平衡的训练集能带来性能提升。我们的结果支持面向失效模式的评测协议以及以拓扑为中心的数据集设计，以服务于可部署的在线建图。
英文原文摘要 1593 字符
Deep learning-based online mapping has emerged as a cornerstone of autonomous driving, yet these models frequently fail to generalize beyond familiar environments. We propose a framework to identify and measure the underlying failure modes by disentangling two effects: Memorization of input features and overfitting to known map topologies. We propose metrics based on evaluation subsets that control for geographical proximity and topological similarity between training and validation scenes. We introduce Frechet distance-based reconstruction statistics that capture per-element shape fidelity without threshold tuning, and define complementary failure-mode scores: an input-feature overfitting score quantifying the performance drop when geographic cues disappear, and a topology overfitting score measuring degradation as scenes become topologically novel. Beyond models, we analyze dataset biases and contribute topology-aware diagnostics: A minimum-spanning-tree (MST) diversity metric for training sets and a symmetric coverage metric to quantify topological similarity between splits. Leveraging these, we formulate an MST-based sparsification strategy that reduces redundancy and improves balancing and performance while shrinking training size. Experiments on nuScenes and Argoverse 2 across multiple state-of-the-art models yield more trustworthy assessment of generalization and show that topology-diverse and balanced training sets lead to improved performance. Our results motivate failure-mode-aware protocols and topology-centric dataset design for deployable online mapping.