R2SNet: 提案精緻化によるクラウドロボティクス環境での物体検出のためのスケーラブルなドメイン適応
R2SNet: Scalable Domain Adaptation for Object Detection in Cloud-Based Robotic Ecosystems via Proposal Refinement
クラウド上の大規模AI推論サービスを利用するロボット向けに、軽量なDNN「R2SNet」をロボット上で走らせて物体検出の提案を再ラベリング・再スコアリング・抑制することで、ドメインシフトによる性能低下を低コストで緩和する手法を提案した。
著者: Michele Antonazzi, Matteo Luperto, N. Alberto Borghese, Nicola Basilico
分類: cs.RO
原文アブストラクト
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.
