Abstract
Dense Bird's Eye View (BEV) semantic maps are central to autonomous driving, yet current multi-camera methods depend on costly, inconsistently annotated BEV ground truth. We address this limitation with a two-phase training strategy for fine-grained road marking segmentation that removes full supervision during pretraining and halves the amount of training data during fine-tuning while still outperforming the comparable supervised baseline model. During the self-supervised pretraining, BEVFormer predictions are differentiably reprojected into the image plane and trained against multi-view semantic pseudo-labels generated by the widely used semantic segmentation model Mask2Former. A temporal loss encourages consistency across frames. The subsequent supervised fine-tuning phase requires only 50% of the dataset and significantly less training time. With our method, the fine-tuning benefits from rich priors learned during pretraining boosting the performance and BEV segmentation quality (up to +2.5pp mIoU over the fully supervised baseline) on nuScenes. It simultaneously halves the usage of annotation data and reduces total training time by up to two thirds. The results demonstrate that differentiable reprojection plus camera perspective pseudo labels yields transferable BEV features and a scalable path toward reduced-label autonomous perception.
Abstract (translated)
稠密的鸟瞰图（BEV）语义地图对于自动驾驶至关重要，然而现有的多相机方法依赖于成本高昂且标注不一致的BEV地面真实数据。我们通过一个两阶段训练策略解决了这一局限性，该策略用于细粒度的道路标记分割任务，在预训练过程中取消了完全监督，并在微调阶段将训练数据量减半，但仍优于可比较的有监督基线模型。在自我监督的预训练期间，BEVFormer预测被差异性地重新投影到图像平面上，并通过广泛使用的语义分割模型Mask2Former生成的多视角语义伪标签进行训练。时间损失鼓励帧之间的连贯性。后续的监督微调阶段仅需要50%的数据集和显著更少的训练时间。使用我们的方法，微调能够从预训练期间学习到的丰富先验中获益，从而提升性能并提高BEV分割质量（在nuScenes数据集中，平均交并比mIoU提高了多达+2.5个百分点）。同时，这种方法将标注数据的使用量减半，并最多减少总训练时间三分之二。实验结果表明，差异性重新投影加上相机视角伪标签能够生成可迁移的BEV特征和一条向低标签自动驾驶感知发展的可扩展路径。
URL
https://arxiv.org/abs/2602.18066
