University of Oulu

Q. Ye et al., "Self-Learning Scene-Specific Pedestrian Detectors Using a Progressive Latent Model," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 2057-2066. doi: 10.1109/CVPR.2017.222

Self-learning scene-specific pedestrian detectors using a progressive latent model

Saved in:
Author: Ye, Qixiang1; Zhang, Tianliang1; Ke, Wei1;
Organizations: 1EECE, University of Chinese Academy of Sciences
2ECE, Duke University
3University of Oulu, Finland
4ASEE, Beihang University
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 1.3 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2017
Publish Date: 2020-03-23


In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human annotation involved. The self-learning approach is deployed as progressive steps of object discovery, object enforcement, and label propagation. In the learning procedure, object locations in each frame are treated as latent variables that are solved with a progressive latent model (PLM). Compared with conventional latent models, the proposed PLM incorporates a spatial regularization term to reduce ambiguities in object proposals and to enforce object localization, and also a graph-based label propagation to discover harder instances in adjacent frames. With the difference of convex (DC) objective functions, PLM can be efficiently optimized with a concave-convex programming and thus guaranteeing the stability of self-learning. Extensive experiments demonstrate that even without annotation the proposed self-learning approach outperforms weakly supervised learning approaches, while achieving comparable performance with transfer learning and fully supervised approaches.

see all

Series: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN: 1063-6919
ISSN-L: 1063-6919
ISBN: 978-1-5386-0457-1
ISBN Print: 978-1-5386-0458-8
Pages: 2057 - 2066
DOI: 10.1109/CVPR.2017.222
Host publication: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Conference: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: This work is partially supported by the NSFC under Grant 61671427, Beijing Municipal Science and Technology Commission under Grant Z161100001616005, and NSF. Tekes and Infotech Oulu are gratefully acknowledged.
Copyright information: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works