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.
@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}
}