Skip to main content

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

Publication ,  Journal Article
Ye, Q; Zhang, T; Ke, W; Qiu, Q; Chen, J; Sapiro, G; Zhang, B
Published in: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
November 6, 2017

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.

Duke Scholars

Published In

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

DOI

Publication Date

November 6, 2017

Volume

2017-January

Start / End Page

2057 / 2066
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Ye, Q., Zhang, T., Ke, W., Qiu, Q., Chen, J., Sapiro, G., & Zhang, B. (2017). Self-learning scene-specific pedestrian detectors using a progressive latent model. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-January, 2057–2066. https://doi.org/10.1109/CVPR.2017.222
Ye, Q., T. Zhang, W. Ke, Q. Qiu, J. Chen, G. Sapiro, and B. Zhang. “Self-learning scene-specific pedestrian detectors using a progressive latent model.” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 2017-January (November 6, 2017): 2057–66. https://doi.org/10.1109/CVPR.2017.222.
Ye Q, Zhang T, Ke W, Qiu Q, Chen J, Sapiro G, et al. Self-learning scene-specific pedestrian detectors using a progressive latent model. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 2017 Nov 6;2017-January:2057–66.
Ye, Q., et al. “Self-learning scene-specific pedestrian detectors using a progressive latent model.” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, Nov. 2017, pp. 2057–66. Scopus, doi:10.1109/CVPR.2017.222.
Ye Q, Zhang T, Ke W, Qiu Q, Chen J, Sapiro G, Zhang B. Self-learning scene-specific pedestrian detectors using a progressive latent model. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 2017 Nov 6;2017-January:2057–2066.

Published In

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

DOI

Publication Date

November 6, 2017

Volume

2017-January

Start / End Page

2057 / 2066