R2SNet：基于提案细化的云机器人生态系统中目标检测的可扩展域自适应
R2SNet: Scalable Domain Adaptation for Object Detection in Cloud-Based Robotic Ecosystems via Proposal Refinement
AI总结：
提出R2SNet轻量级架构，在机器人本地进行提案细化（重标记、重评分、抑制），实现云机器人场景中目标检测的可扩展域自适应，门检测实验验证有效。
摘要：
我们提出了一种新颖的方法，用于云机器人场景中的可扩展域自适应，在该场景中，机器人依赖由大型预训练深度神经网络驱动的第三方AI推理服务。我们的方法基于在机器人本地运行的下游提案细化阶段，利用一种新的轻量级DNN架构R2SNet。该架构旨在通过将目标检测过程适应目标环境，专注于边界框提案的重新标记、重新评分和抑制，来缓解域偏移导致的性能下降。我们的方法允许在机器人上本地执行，解决了域自适应的可扩展性挑战，而不会产生显著的计算成本。在移动服务机器人执行门检测任务上的实际结果表明，所提出的方法在实现可扩展域自适应方面的有效性。
英文摘要：
We introduce a novel approach for scalable domain adaptation in cloud robotics scenarios where robots rely on third-party AI inference services powered by large pre-trained deep neural networks. Our method is based on a downstream proposal-refinement stage running locally on the robots, exploiting a new lightweight DNN architecture, R2SNet. This architecture aims to mitigate performance degradation from domain shifts by adapting the object detection process to the target environment, focusing on relabeling, rescoring, and suppression of bounding-box proposals. Our method allows for local execution on robots, addressing the scalability challenges of domain adaptation without incurring significant computational costs. Real-world results on mobile service robots performing door detection show the effectiveness of the proposed method in achieving scalable domain adaptation.
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。
