Abstract

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can learn to detect novel objects from only a few annotated examples. Our proposed model leverages fully labeled base classes and quickly adapts to novel classes, using a meta feature learner and a reweighting module within a one-stage detection architecture. The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples. The reweighting module transforms a few support examples from the novel classes to a global vector that indicates the importance or relevance of meta features for detecting the corresponding objects. These two modules, together with a detection prediction module, are trained end-to-end based on an episodic few-shot learning scheme and a carefully designed loss function. Through extensive experiments we demonstrate that our model outperforms well-established baselines by a large margin for few-shot object detection, on multiple datasets and settings. We also present analysis on various aspects of our proposed model, aiming to provide some inspiration for future few-shot detection works.

Paper

Bingyi Kang, Zhuang Liu, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell Few Shot Object Detection via Feature Reweighting ICCV 2019

Code

github.com/bingykang/Fewshot_Detection

Citation

@inproceedings{kang2019few,
  title={Few-shot Object Detection via Feature Reweighting},
  author={Kang, Bingyi and Liu, Zhuang and Wang, Xin and Yu, Fisher and Feng, Jiashi and Darrell, Trevor},
  booktitle={ICCV},
  year={2019}
}