Affordable Access

Access to the full text

Leveraging Prior-Knowledge for Weakly Supervised Object Detection Under a Collaborative Self-Paced Curriculum Learning Framework

Authors
  • Zhang, Dingwen1
  • Han, Junwei1
  • Zhao, Long1
  • Meng, Deyu2
  • 1 Northwestern Polytechnical University, School of Automation, Xi’an, 710072, China , Xi’an (China)
  • 2 Xi’an Jiaotong University, Institute for Information and System Sciences, Science and Ministry of Education Key Lab for Intelligent Networks and Network Security, Xi’an, China , Xi’an (China)
Type
Published Article
Journal
International Journal of Computer Vision
Publisher
Springer-Verlag
Publication Date
Aug 28, 2018
Volume
127
Issue
4
Pages
363–380
Identifiers
DOI: 10.1007/s11263-018-1112-4
Source
Springer Nature
Keywords
License
Yellow

Abstract

Weakly supervised object detection is an interesting yet challenging research topic in computer vision community, which aims at learning object models to localize and detect the corresponding objects of interest only under the supervision of image-level annotation. For addressing this problem, this paper establishes a novel weakly supervised learning framework to leverage both the instance-level prior-knowledge and the image-level prior-knowledge based on a novel collaborative self-paced curriculum learning (C-SPCL) regime. Under the weak supervision, C-SPCL can leverage helpful prior-knowledge throughout the whole learning process and collaborate the instance-level confidence inference with the image-level confidence inference in a robust way. Comprehensive experiments on benchmark datasets demonstrate the superior capacity of the proposed C-SPCL regime and the proposed whole framework as compared with state-of-the-art methods along this research line.

Report this publication

Statistics

Seen <100 times