Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them

• URL: http://arxiv.org/abs/2603.19852v1
• Date: Fri, 20 Mar 2026 11:09:11 GMT
• Title: Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them
• Abstract summary: 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 geometries.<n>We introduce Fréchet distance-based reconstruction statistics that capture per-element shape fidelity without threshold tuning.<n>We formulate an MST-based sparsification strategy that reduces redundancy and improves balancing and performance while shrinking training size.
• Score: 10.503307305047487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 geometries. We propose measures based on evaluation subsets that control for geographical proximity and geometric similarity between training and validation scenes. We introduce Fréchet distance-based reconstruction statistics that capture per-element shape fidelity without threshold tuning, and define complementary failure-mode scores: a localization overfitting score quantifying the performance drop when geographic cues disappear, and a map geometry overfitting score measuring degradation as scenes become geometrically novel. Beyond models, we analyze dataset biases and contribute map geometry-aware diagnostics: A minimum-spanning-tree (MST) diversity measure for training sets and a symmetric coverage measure to quantify geometric 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 map geometry-diverse and balanced training sets lead to improved performance. Our results motivate failure-mode-aware protocols and map geometry-centric dataset design for deployable online mapping.

Related papers

• Learning Point Cloud Geometry as a Statistical Manifold: Theory and Practice [11.695017334165287]
  LiDAR-acquired point clouds are inherently sparse and non-uniform.<n>Existing approaches attempt to compensate for these limitations by estimating local geometry.<n>We introduce Point-to-Ellipsoid (POLI), a deep neural estimator that predicts per-point Gaussian geometry.
  arXiv  Detail & Related papers  (2026-05-11T12:27:25Z)
• VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment [15.619170225414571]
  Video diffusion models lack explicit geometric supervision during training, leading to inconsistency artifacts.<n>We propose a geometry-based reward model that leverages pretrained geometric foundation models to evaluate multi-view consistency.<n>Our approach conducts error computation in a pointwise fashion, yielding a more physically grounded and robust error metric.
  arXiv  Detail & Related papers  (2026-03-17T09:04:10Z)
• Graph Smoothing for Enhanced Local Geometry Learning in Point Cloud Analysis [19.545338629365894]
  Graph-based methods have proven to be effective in capturing relationships among points for 3D point cloud analysis.<n>These methods often suffer from suboptimal graph structures due to sparse connections at boundary points and noisy connections in junction areas.<n>We introduce a graph smoothing module designed to optimize the graph structure and minimize the negative impact of unreliable sparse and noisy connections.
  arXiv  Detail & Related papers  (2026-01-16T09:01:44Z)
• MS-ISSM: Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity [65.85858856481131]
  unstructured and irregular nature of point clouds poses a significant challenge for objective quality assessment (PCQA)<n>We propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM)
  arXiv  Detail & Related papers  (2026-01-03T14:58:52Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• G-MSM: Unsupervised Multi-Shape Matching with Graph-based Affinity Priors [52.646396621449]
  G-MSM is a novel unsupervised learning approach for non-rigid shape correspondence. We construct an affinity graph on a given set of training shapes in a self-supervised manner. We demonstrate state-of-the-art performance on several recent shape correspondence benchmarks.
  arXiv  Detail & Related papers  (2022-12-06T12:09:24Z)
• Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry [3.712728573432119]
  We develop a standardized parameterization in which all symmetries are removed, resulting in a toroidal topology. We derive a meaningful notion of the flatness of minimizers and of the geodesic paths connecting them. We also find that minimizers found by variants of gradient descent can be connected by zero-error paths with a single bend.
  arXiv  Detail & Related papers  (2022-02-07T09:57:54Z)
• Deep Relational Metric Learning [84.95793654872399]
  This paper presents a deep relational metric learning framework for image clustering and retrieval. We learn an ensemble of features that characterizes an image from different aspects to model both interclass and intraclass distributions. Experiments on the widely-used CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate that our framework improves existing deep metric learning methods and achieves very competitive results.
  arXiv  Detail & Related papers  (2021-08-23T09:31:18Z)
• Visual SLAM with Graph-Cut Optimized Multi-Plane Reconstruction [11.215334675788952]
  This paper presents a semantic planar SLAM system that improves pose estimation and mapping using cues from an instance planar segmentation network. While the mainstream approaches are using RGB-D sensors, employing a monocular camera with such a system still faces challenges such as robust data association and precise geometric model fitting.
  arXiv  Detail & Related papers  (2021-08-09T18:16:08Z)
• CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency [61.40511574314069]
  Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. We propose CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors.
  arXiv  Detail & Related papers  (2021-06-20T08:20:56Z)
• GELATO: Geometrically Enriched Latent Model for Offline Reinforcement Learning [54.291331971813364]
  offline reinforcement learning approaches can be divided into proximal and uncertainty-aware methods. In this work, we demonstrate the benefit of combining the two in a latent variational model. Our proposed metrics measure both the quality of out of distribution samples as well as the discrepancy of examples in the data.
  arXiv  Detail & Related papers  (2021-02-22T19:42:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.