一次训练多处部署：基于极坐标的自适应BEV感知用于自动驾驶
One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Driving
AI总结：
针对车载芯片算力不同导致模型需多次训练的问题，提出基于极坐标表示的自适应BEV感知方法，通过极坐标空间特征自适应采样与多尺度上下文交互，实现一次训练多处部署并取得优异性能。
摘要：
当前车载芯片通常具有不同的算力，这意味着需要多次训练过程才能使同一个基于学习的算法适应不同的芯片，耗费大量计算资源。对于具有大模型的3D感知方法而言，情况变得更加糟糕。以往以视觉为中心的3D感知方法使用固定分辨率的规则网格表示特征图进行训练，这不适用于适应其他网格尺度，限制了更广泛的部署。在本文中，我们在从图像构建BEV特征图时利用极坐标（Polar）表示，以实现一次训练多处部署的目标。具体而言，极坐标空间中沿射线的特征可以轻松地进行自适应采样，并投影到任意分辨率的笛卡尔空间特征中。为了进一步提高适应能力，我们使多尺度上下文信息相互交互以增强特征表示。在大规模自动驾驶数据集上的实验表明，就一次训练多处部署的良好特性而言，我们的方法优于其他方法。
英文摘要：
Current on-board chips usually have different computing power, which means multiple training processes are needed for adapting the same learning-based algorithm to different chips, costing huge computing resources. The situation becomes even worse for 3D perception methods with large models. Previous vision-centric 3D perception approaches are trained with regular grid-represented feature maps of fixed resolutions, which is not applicable to adapt to other grid scales, limiting wider deployment. In this paper, we leverage the Polar representation when constructing the BEV feature map from images in order to achieve the goal of training once for multiple deployments. Specifically, the feature along rays in Polar space can be easily adaptively sampled and projected to the feature in Cartesian space with arbitrary resolutions. To further improve the adaptation capability, we make multi-scale contextual information interact with each other to enhance the feature representation. Experiments on a large-scale autonomous driving dataset show that our method outperforms others as for the good property of one training for multiple deployments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
