期刊
COMPUTER VISION, ECCV 2022, PT XXXIX
卷 13699, 期 -, 页码 427-444出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-031-19842-7_25
关键词
Few-shot object detection; Online; Robot exploration
资金
- ONR [N0014-19-1-2266]
- ARL DCIST CRA award [W911NF-17-2-0181]
Few-shot object detection has gained increasing attention and progress, but the requirement of offline fine-tuning stage hinders its usage in online applications. The proposed AirDet architecture achieves comparable or better results without fine-tuning by learning class-agnostic relation with support images.
Few-shot object detection has attracted increasing attention and rapidly progressed in recent years. However, the requirement of an exhaustive offline fine-tuning stage in existing methods is timeconsuming and significantly hinders their usage in online applications such as autonomous exploration of low-power robots. We find that their major limitation is that the little but valuable information from a few support images is not fully exploited. To solve this problem, we propose a brand new architecture, AirDet, and surprisingly find that, by learning class-agnostic relation with the support images in all modules, including cross-scale object proposal network, shots aggregation module, and localization network, AirDet without fine-tuning achieves comparable or even better results than many fine-tuned methods, reaching up to 3040% improvements. We also present solid results of onboard tests on real-world exploration data from the DARPA Subterranean Challenge, which strongly validate the feasibility of AirDet in robotics. To the best of our knowledge, AirDet is the first feasible few-shot detection method for autonomous exploration of low-power robots. The code and pre-trained models are released at https://github.com/Jaraxxus-Me/AirDet.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据