DSFNet:学习解耦场景分解用于多场景路线排序
DSFNet: Learning Disentangled Scenario Factorization for Multi-Scenario Route Ranking
AI总结:
针对多场景路线排序中场景数量爆炸、高度纠缠和高容量需求等挑战,本文提出DSFNet,通过解耦场景分解网络及场景感知技术,并构建首个公开数据集MSDR,已在工业界验证其有效性。
摘要:
多场景路线排序(MSRR)在许多工业地图系统中至关重要。然而,工业界主要采用交互式界面来鼓励用户选择预定义场景,这可能阻碍下游排序性能。此外,在学术界,多场景排序工作仅来自其他领域,由于缺乏公开可用的MSRR数据集,没有专门针对路线数据的研究。而且,所有现有的多场景工作仍未能同时解决MSRR的三个具体挑战,即场景数量爆炸、高度纠缠和高容量需求。与以往不同,为解决MSRR,我们的关键思想是将路线排序中的复杂场景分解为若干解耦的因子场景模式。据此,我们提出了一种新方法——解耦场景分解网络(DSFNet),它基于高容量的多因子场景分支结构灵活地组合场景相关参数。然后,提出了一种新颖的正则化方法来诱导因子场景的解耦。此外,还开发了两种额外的新技术,即场景感知批归一化和场景感知特征过滤,以提高网络对场景表示的感知能力。另外,为促进学术界的MSRR研究,我们提出了MSDR,这是第一个大规模公开可用的带标注工业多场景驾驶路线数据集。综合实验结果表明了我们的DSFNet的优越性,该网络已成功部署在高德地图中,服务于主要在线流量。
英文摘要:
Multi-scenario route ranking (MSRR) is crucial in many industrial mapping systems. However, the industrial community mainly adopts interactive interfaces to encourage users to select pre-defined scenarios, which may hinder the downstream ranking performance. In addition, in the academic community, the multi-scenario ranking works only come from other fields, and there are no works specifically focusing on route data due to lacking a publicly available MSRR dataset. Moreover, all the existing multi-scenario works still fail to address the three specific challenges of MSRR simultaneously, i.e. explosion of scenario number, high entanglement, and high-capacity demand. Different from the prior, to address MSRR, our key idea is to factorize the complicated scenario in route ranking into several disentangled factor scenario patterns. Accordingly, we propose a novel method, Disentangled Scenario Factorization Network (DSFNet), which flexibly composes scenario-dependent parameters based on a high-capacity multi-factor-scenario-branch structure. Then, a novel regularization is proposed to induce the disentanglement of factor scenarios. Furthermore, two extra novel techniques, i.e. scenario-aware batch normalization and scenario-aware feature filtering, are developed to improve the network awareness of scenario representation. Additionally, to facilitate MSRR research in the academic community, we propose MSDR, the first large-scale publicly available annotated industrial Multi-Scenario Driving Route dataset. Comprehensive experimental results demonstrate the superiority of our DSFNet, which has been successfully deployed in AMap to serve the major online traffic.
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。