English

Team PFDet's Methods for Open Images Challenge 2019

Computer Vision and Pattern Recognition 2019-10-28 v1

Abstract

We present the instance segmentation and the object detection method used by team PFDet for Open Images Challenge 2019. We tackle a massive dataset size, huge class imbalance and federated annotations. Using this method, the team PFDet achieved 3rd and 4th place in the instance segmentation and the object detection track, respectively.

Keywords

Cite

@article{arxiv.1910.11534,
  title  = {Team PFDet's Methods for Open Images Challenge 2019},
  author = {Yusuke Niitani and Toru Ogawa and Shuji Suzuki and Takuya Akiba and Tommi Kerola and Kohei Ozaki and Shotaro Sano},
  journal= {arXiv preprint arXiv:1910.11534},
  year   = {2019}
}
R2 v1 2026-06-23T11:54:33.602Z