发表机构
North Carolina State University（北卡罗来纳州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对自动驾驶汽车视觉模型泛化差的问题，提出AdaptAV系统，利用云端专家模型指导车载模型的持续重新训练，以逐步提升感知推理精度。
AI 中文摘要
将视觉感知模型部署到自动驾驶汽车时，需优先考虑推理速度，因此会采用架构更浅、参数更少（即经过更多剪枝）的模型。这类小型模型的泛化能力不佳，在遇到新场景时可能导致性能下降。我们提出一种系统，通过利用车辆上传的数据在云端持续重新训练视觉模型来解决该问题。我们借助云端丰富的计算资源（包括机器学习加速器）运行高精度的专家模型，该模型将指导车载模型的重新训练过程。新训练完成的模型会通过网络传输到车辆，供车辆用于感知任务，最终实现推理精度随时间提升。
英文摘要
Deploying vision perception models in autonomous vehicles requires that we prioritize inference speeds, resulting in a model with shallower architectures and lesser model parameters (i.e., more pruned). Such small models do not generalize well, which could result in poor performance when encountered with novel scenarios. We propose a system that overcomes this by continuously retraining the vision models on the cloud with data uploaded by vehicles. We leverage the abundant compute resources, including machine learning accelerators, of the cloud to run a highly-accurate oracle model that will guide the retraining process of the on-vehicle model. This newly trained model is transmitted to the vehicle over the network and is utilized by the vehicle for perceptions, leading to improved inference accuracy over time.
Comments7 pages, 11 figures
Journal ref2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall), Washington, DC, USA, 2024, pp. 1-7
DOI：10.1109/VTC2024-Fall63153.2024.10757493
