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.

介绍了一种大规模实时物体检测器 R-FCN-3000，其中物体探测和分类被解耦。通过将物体探测得分和细粒度分类得分相乘来获得 RoI 的检测得分。R-FCN-3000 在 ImageNet 检测数据集上获得 34.9% 的 mAP，并在每秒处理 30 张图像的情况下胜过 YOLO-9000 18%。我们还展示了 R-FCN-3000 学习到的 objectness 可以推广到新的类别，并且随着训练对象类别的数量增加而提高性能，支持学习通用对象探测器的假设。