GradingNet: Towards Providing Reliable Supervisions for Weakly Supervised Object Detection by Grading the Box Candidates

Authors

  • Qifei Jia Institute of Information Science, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China
  • Shikui Wei Institute of Information Science, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China
  • Tao Ruan Institute of Information Science, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China
  • Yufeng Zhao China Academy of Chinese Medical Sciences, Beijing, China
  • Yao Zhao Institute of Information Science, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing, China

Keywords:

Object Detection & Categorization

Abstract

Weakly-Supervised Object Detection (WSOD) aims at training a model with limited and coarse annotations for precisely locating the regions of objects. Existing works solve the WSOD problem by using a two-stage framework, i.e., generating candidate bounding boxes with weak supervision information and then refining them by directly employing supervised object detection models. However, most of such works mainly focus on the performance boosting of the first stage, while ignoring the better usage of generated candidate bounding boxes. To address this issue, we propose a new two-stage framework for WSOD, named GradingNet, which can make good use of the generated candidate bounding boxes. Specifically, the proposed GradingNet consists of two modules: Boxes Grading Module (BGM) and Informative Boosting Module (IBM). BGM generates proposals of the bounding boxes by using standard one-stage weakly-supervised methods, then utilizes Inclusion Principle to pick out highly-reliable boxes and evaluate the grade of each box. With the above boxes and their grade information, an effective anchor generator and a grade-aware loss are carefully designed to train the IBM. Taking the advantages of the grade information, our GradingNet achieves state-of-the-art performance on COCO, VOC 2007 and VOC 2012 benchmarks.

Downloads

Published

2021-05-18

How to Cite

Jia, Q., Wei, S., Ruan, T., Zhao, Y., & Zhao, Y. (2021). GradingNet: Towards Providing Reliable Supervisions for Weakly Supervised Object Detection by Grading the Box Candidates. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1682-1690. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16261

Issue

Section

AAAI Technical Track on Computer Vision I