1 Hit in 2.0 sec

AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration [article]

Bowen Li, Chen Wang, Pranay Reddy, Seungchan Kim, Sebastian Scherer
2022 arXiv   pre-print
To the best of our knowledge, AirDet is the first feasible few-shot detection method for autonomous exploration of low-power robots.  ...  proposal network, shots aggregation module, and localization network, AirDet without fine-tuning achieves comparable or even better results than the exhaustively fine-tuned methods, reaching up to 30-40%  ...  Solid lines denote results with no fine-tuning and dashed lines indicate results fine-tuned on few-shot data. Without further updating, AirDet can outperform prior work.  ... 
arXiv:2112.01740v2 fatcat:jut2jnw2vnes7fv3vrzzaosxse