用合成数据提升目标检测器跨域适应能力，不丢掉原有性能。
MORDA: A Synthetic Dataset to Facilitate Adaptation of Object Detectors to Unseen Real-target Domain While Preserving Performance on Real-source Domain
- 构建混合真实特征的合成数据集MORDA，模拟韩国道路环境。
- 仅用nuScenes和MORDA训练的模型在韩国实测数据上mAP显著提升。
- 适合需要跨区域部署的自动驾驶感知系统研发人员。
基于深度神经网络的感知模型在自动驾驶开发中至关重要，但其对大规模高质量数据的依赖带来了高昂的数据采集与标注成本。此外，当自动驾驶车辆需部署至新地区（真实目标域）时，现有数据集可能无法覆盖，需重新收集。为缓解这一负担，我们提出利用合成环境作为辅助域，复现真实域特征，以低成本、高效方式实现对目标域的间接经验学习。以nuScenes代表真实源域，韩国为真实目标域，我们构建了韩国多个区域的数字孪生，并复现nuScenes的数据采集框架。将上述组件融合于仿真器中，生成合成融合域，创建新型驾驶数据集MORDA（Mixture Of Real-domain characteristics for synthetic-data-assisted Domain Adaptation）。通过仅在nuScenes与MORDA组合数据上训练2D/3D检测器，评估其在未见过的真实数据集AI-Hub（韩国采集）上的表现。实验表明，MORDA能显著提升AI-Hub上的平均精度均值（mAP），同时保持或略微提升在nuScenes上的性能。
原文摘要 · Abstract (English)
Deep neural network (DNN) based perception models are indispensable in the development of autonomous vehicles (AVs). However, their reliance on large-scale, high-quality data is broadly recognized as a burdensome necessity due to the substantial cost of data acquisition and labeling. Further, the issue is not a one-time concern, as AVs might need a new dataset if they are to be deployed to another region (real-target domain) that the in-hand dataset within the real-source domain cannot incorporate. To mitigate this burden, we propose leveraging synthetic environments as an auxiliary domain where the characteristics of real domains are reproduced. This approach could enable indirect experience about the real-target domain in a time- and cost-effective manner. As a practical demonstration of our methodology, nuScenes and South Korea are employed to represent real-source and real-target domains, respectively. That means we construct digital twins for several regions of South Korea, and the data-acquisition framework of nuScenes is reproduced. Blending the aforementioned components within a simulator allows us to obtain a synthetic-fusion domain in which we forge our novel driving dataset, MORDA: Mixture Of Real-domain characteristics for synthetic-data-assisted Domain Adaptation. To verify the value of synthetic features that MORDA provides in learning about driving environments of South Korea, 2D/3D detectors are trained solely on a combination of nuScenes and MORDA. Afterward, their performance is evaluated on the unforeseen real-world dataset (AI-Hub) collected in South Korea. Our experiments present that MORDA can significantly improve mean Average Precision (mAP) on AI-Hub dataset while that on nuScenes is retained or slightly enhanced.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。