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
FrameScope是面向自动驾驶汽车持续学习的时序数据估值框架，将神经正切核理论扩展到时域，通过车辆端局部帧选择降低带宽需求，提升样本效率并减少感知的灾难性遗忘，性能优于现有方法。
AI 中文摘要
自动驾驶汽车在动态多变的环境中运行，不断出现新场景和边缘案例，静态学习模型无法保障安全可靠运行，持续学习对适应环境变化、维持不同真实场景下的鲁棒性能至关重要。然而自动驾驶汽车运行时会产生大量视觉数据流，现有持续学习方法通常依赖启发式采样，无法捕捉时序动态，常忽略关键学习机会或选择冗余帧。本文提出FrameScope——一种面向自动驾驶汽车持续学习的时序数据估值框架，将神经正切核理论扩展到时域，实现对流视觉数据的原则性估值。与以云为中心、传输所有视频数据进行处理的方法不同，该方法在车辆端执行原则性的局部帧选择，仅向云端神谕模型查询高价值帧的标签。在多个领域偏移场景下的大量实验表明，FrameScope始终优于现有方法，样本效率更高，显著降低自动驾驶汽车感知中的灾难性遗忘；通过在车辆端对数据估值并仅查询所选帧的标签，FrameScope降低了带宽需求，使轻量级云标注服务可实现规模化运行。
英文摘要
Autonomous vehicles operate in dynamic, ever-changing environments where new scenarios and edge cases constantly emerge. As a result, static learning models are inadequate for ensuring safe and reliable operation. Continuous learning is essential for adapting to these evolving conditions and maintaining robust performance across diverse real-world settings. However, autonomous vehicles generate massive streams of visual data during operation, and existing continuous learning approaches typically rely on heuristic sampling methods that fail to capture temporal dynamics, often overlooking critical learning opportunities or selecting redundant frames. In this paper, we introduce FrameScope, a temporal data valuation framework for continuous learning in autonomous vehicles. FrameScope extends neural tangent kernel theory to temporal domains, enabling principled valuation of streaming visual data. Unlike cloud-centric methods that transmit all video data for processing, our approach performs principled, local frame selection on the vehicle and queries a cloud-based oracle model only for labels of those high-value frames. Extensive experiments across multiple domain shifts show that FrameScope consistently outperforms existing methods, achieving higher sample efficiency and significantly reducing catastrophic forgetting in autonomous vehicle perception. By valuing data on the vehicle and querying only labels for selected frames, FrameScope reduces bandwidth requirements, enabling scalable operation with a lightweight cloud labeling service.
Comments15 pages
Journal refProceedings of the Tenth ACM/IEEE Symposium on Edge Computing (SEC 2025), Article 13, 15 pages
