English

R-FCN-3000 at 30fps: Decoupling Detection and Classification

Computer Vision and Pattern Recognition 2017-12-06 v1

Abstract

We present R-FCN-3000, a large-scale real-time object detector in which objectness detection and classification are decoupled. To obtain the detection score for an RoI, we multiply the objectness score with the fine-grained classification score. Our approach is a modification of the R-FCN architecture in which position-sensitive filters are shared across different object classes for performing localization. For fine-grained classification, these position-sensitive filters are not needed. R-FCN-3000 obtains an mAP of 34.9% on the ImageNet detection dataset and outperforms YOLO-9000 by 18% while processing 30 images per second. We also show that the objectness learned by R-FCN-3000 generalizes to novel classes and the performance increases with the number of training object classes - supporting the hypothesis that it is possible to learn a universal objectness detector. Code will be made available.

Keywords

Cite

@article{arxiv.1712.01802,
  title  = {R-FCN-3000 at 30fps: Decoupling Detection and Classification},
  author = {Bharat Singh and Hengduo Li and Abhishek Sharma and Larry S. Davis},
  journal= {arXiv preprint arXiv:1712.01802},
  year   = {2017}
}

Comments

CVPR 2018 submission

R2 v1 2026-06-22T23:07:42.514Z