DBC: Learning Offset Probability Distribution for Accurate Object Detection

DBC is an extend version of our previous work BC (Offset Bin Classification Network for Accurate Object Detection) published at CVPR2020.
We will release the code and related models as soon as possible, please wait...

Prerequisites

  • Linux or macOS (Windows is in experimental support)
  • Python 3.6+
  • PyTorch 1.3+
  • CUDA 9.2+ (If you build PyTorch from source, CUDA 9.0 is also compatible)
  • GCC 5+
  • MMCV

@inproceedings{qiu2020offset,
title={Offset bin classification network for accurate object detection},
author={Qiu, Heqian and Li, Hongliang and Wu, Qingbo and Shi, Hengcan},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={13188--13197},
year={2020}
}