• Menü menu
  • menu open menu
Publications
Digital

Few-shot Object Detection Using Online Random Forests

Contributing authors of JOANNEUM RESEARCH:
Authors
Bailer, Werner; Fassold, Hannes
Abstract:
We propose an approach for few-shot object detection, consisting of a CNN-based generic object detector and feature extractor, and an online random forest as a classifier. This enables incremental training of the classifier, which reaches similar performance with around 20 samples as when using 50+ training samples in batch learning
Title:
Few-shot Object Detection Using Online Random Forests
Seiten:
pp95-97
Publikationsdatum
2020

Publikationsreihe

Proceedings
Proceedings of the Joint Austrian Computer Vision and Robotics Workshop 2020

Related publications

Skip to content