发表机构
Nissan Advanced Technology Center - Silicon Valley; Nissan North America（日产先进技术中心 - 硅谷; 日产北美公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对在线高清地图构建的标注数据稀缺问题，提出带置信感知伪标签的师生半监督学习框架，在nuScenes数据集低标注 regime下使mAP提升6.1，有效缓解数据稀缺困境。
AI 中文摘要
将在线高清地图构建系统部署到实际场景面临的关键挑战是标注训练数据稀缺，这会限制模型在多样化环境中的泛化能力。为解决该问题，我们提出一种师生半监督学习（SSL）框架，通过置信感知地图精修从未标注数据生成高质量伪标签。该方法首先在有限标注数据上训练教师模型，再利用基于Beta分布的置信度图评估不同时间观测下预测地图元素的可靠性。与丢弃整个元素的传统过滤方法不同，我们引入空间裁剪技术，选择性保留高置信度区域同时移除不可靠片段。精修后的地图元素作为地图先验，在第二轮迭代中提升教师模型对未标注数据的预测精度。这些增强后的预测结果作为伪标签，用于从头训练学生模型，随后在原始标注数据上微调。在nuScenes数据集上的实验结果表明，与仅在标注数据上训练相比，我们的采用精修伪标签的师生框架在低标注 regime 下mAP提升了6.1，为在线高清地图构建中的标注数据稀缺问题提供了实用解决方案。
英文摘要
A critical challenge in deploying online HD map construction systems to real-world scenarios is the scarcity of labeled training data, which limits model generalization in diverse environments. To address this limitation, we propose a teacher-student semi-supervised learning (SSL) framework that generates high-quality pseudo-labels from unlabeled data through confidence-aware map refinement. Our approach first trains a teacher model on limited labeled data, then leverages Beta-distribution-based confidence maps to assess the reliability of predicted map elements across temporal observations. Unlike conventional filtering methods that discard entire elements, we introduce a spatial clipping technique that selectively preserves high-confidence regions while removing unreliable segments. The refined map elements serve as map priors that improve the teacher model's prediction accuracy on unlabeled data in a second pass. These enhanced predictions become pseudo-labels for training a student model from scratch, followed by fine-tuning on the original labeled data. Experimental results on the nuScenes dataset demonstrate that our teacher-student framework with refined pseudo-labels improves performance by +6.1 mAP under a low-label regime compared to training on labeled data alone, offering a practical solution to the labeled data scarcity problem in online HD map construction.
Comments17 pages, 4 figures, Accepted at ECCV 2026 DriveX Workshop on Foundation Models for Autonomous Driving
