AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration
Bowen Li, Chen Wang, Pranay Reddy, Seungchan Kim, Sebastian Scherer

TL;DR
AirDet introduces a novel few-shot detection architecture that operates without fine-tuning, leveraging class-agnostic relations to achieve high accuracy in autonomous exploration tasks, validated by real-world robotics tests.
Contribution
AirDet is the first few-shot detection method designed specifically for autonomous exploration without requiring fine-tuning, utilizing class-agnostic relations across modules.
Findings
Achieves comparable or better results than fine-tuned methods.
Reaches 30-40% improvements in detection performance.
Validated on real-world DARPA Subterranean Challenge data.
Abstract
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 time-consuming 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 30-40% improvements. We also present solid results of onboard…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Advanced Neural Network Applications · Domain Adaptation and Few-Shot Learning
