CoVIO：面向视觉-惯性里程计的在线持续学习
CoVIO: Online Continual Learning for Visual-Inertial Odometry
AI总结：
本文提出CoVIO，一种面向视觉-惯性里程计的在线持续学习方法，通过多样性优先的经验回放采样策略和异步更新机制，在嵌入式设备上实现实时连续推理并有效缓解灾难性遗忘。
摘要：
视觉里程计是移动设备和机器人平台上许多应用的基础任务。由于此类应用通常并不局限于预定义的目标领域，且基于学习的视觉系统已知对未见环境的泛化能力较差，因此在推理过程中进行持续适应的方法具有重要研究价值。本文提出CoVIO，用于视觉-惯性里程计的在线持续学习。CoVIO通过利用经验回放，在有效适应新领域的同时缓解灾难性遗忘。特别地，我们提出一种新颖的采样策略，在固定大小的回放缓冲区中最大化图像多样性，以应对嵌入式设备有限的存储容量。我们还进一步提供了异步版本，将里程计估计与网络权重更新步骤解耦，从而支持实时连续推理。我们在多个真实世界数据集上对CoVIO进行了广泛评估，证明其能够成功适应新领域，并优于先前方法。本文代码已公开，访问地址为http://continual-slam.cs.uni-freiburg.de。
英文摘要：
Visual odometry is a fundamental task for many applications on mobile devices and robotic platforms. Since such applications are oftentimes not limited to predefined target domains and learning-based vision systems are known to generalize poorly to unseen environments, methods for continual adaptation during inference time are of significant interest. In this work, we introduce CoVIO for online continual learning of visual-inertial odometry. CoVIO effectively adapts to new domains while mitigating catastrophic forgetting by exploiting experience replay. In particular, we propose a novel sampling strategy to maximize image diversity in a fixed-size replay buffer that targets the limited storage capacity of embedded devices. We further provide an asynchronous version that decouples the odometry estimation from the network weight update step enabling continuous inference in real time. We extensively evaluate CoVIO on various real-world datasets demonstrating that it successfully adapts to new domains while outperforming previous methods. The code of our work is publicly available at http://continual-slam.cs.uni-freiburg.de.
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。
