论文标题
桥接域间隙以获得多代理感知
Bridging the Domain Gap for Multi-Agent Perception
论文作者
论文摘要
现有的多代理感知算法通常选择共享从代理之间的原始感应数据中提取的深神经特征，从而在准确性和通信带宽限制之间实现了权衡。但是，这些方法假定所有代理都具有相同的神经网络，这在现实世界中可能不实用。当模型不同时，传输的功能可能具有较大的域间隙，从而导致多代理感知的性能下降。在本文中，我们提出了第一个轻巧的框架来弥合此类域差距以进行多机构感知，这对于大多数现有系统而言，可以在维护机密性的同时是插件模块。我们的框架包括一个可学习的功能resizer，可在多个维度上对齐功能，以及用于域自适应的稀疏跨域变压器。对公共多代理感知数据集V2XSET进行的广泛实验表明，我们的方法可以有效地弥合来自不同域中的特征的差距，并且基于点云的3D对象检测的特征至少高于至少8％。
Existing multi-agent perception algorithms usually select to share deep neural features extracted from raw sensing data between agents, achieving a trade-off between accuracy and communication bandwidth limit. However, these methods assume all agents have identical neural networks, which might not be practical in the real world. The transmitted features can have a large domain gap when the models differ, leading to a dramatic performance drop in multi-agent perception. In this paper, we propose the first lightweight framework to bridge such domain gaps for multi-agent perception, which can be a plug-in module for most existing systems while maintaining confidentiality. Our framework consists of a learnable feature resizer to align features in multiple dimensions and a sparse cross-domain transformer for domain adaption. Extensive experiments on the public multi-agent perception dataset V2XSet have demonstrated that our method can effectively bridge the gap for features from different domains and outperform other baseline methods significantly by at least 8% for point-cloud-based 3D object detection.
