CVOct 25, 2019
Team PFDet's Methods for Open Images Challenge 2019
arXiv:1910.11534v13 citations
Originality Synthesis-oriented
AI Analysis
This work addresses dataset and annotation issues for computer vision tasks, but it is incremental as it applies existing methods to a specific competition.
The paper tackled the challenges of massive dataset size, huge class imbalance, and federated annotations in the Open Images Challenge 2019, achieving 3rd place in instance segmentation and 4th place in object detection.
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.