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

Bharat Singh, Hengduo Li, Abhishek Sharma, Larry S. Davis; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 1081-1090

Abstract


We propose a modular approach towards large-scale real-time object detection by decoupling objectness detection and classification. We exploit the fact that many object classes are visually similar and share parts. Thus, a universal objectness detector can be learned for class-agnostic object detection followed by fine-grained classification using a (non)linear classifier. Our approach is a modification of the R-FCN architecture to learn shared filters for performing localization across different object classes. We trained a detector for 3000 object classes, called R-FCN-3000, that obtains an mAP of 34.9% on the ImageNet detection dataset. It 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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Singh_2018_CVPR,
author = {Singh, Bharat and Li, Hengduo and Sharma, Abhishek and Davis, Larry S.},
title = {R-FCN-3000 at 30fps: Decoupling Detection and Classification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}