Deep Self-Taught Learning for Weakly Supervised Object Localization

@article{Jie2017DeepSL,
  title={Deep Self-Taught Learning for Weakly Supervised Object Localization},
  author={Zequn Jie and Yunchao Wei and Xiaojie Jin and Jiashi Feng and Wei Liu},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={4294-4302}
}
Most existing weakly supervised localization (WSL) approaches learn detectors by finding positive bounding boxes based on features learned with image-level supervision. However, those features do not contain spatial location related information and usually provide poor-quality positive samples for training a detector. To overcome this issue, we propose a deep self-taught learning approach, which makes the detector learn the object-level features reliable for acquiring tight positive samples and… CONTINUE READING
Highly Cited
This paper has 50 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 29 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 34 extracted citations

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

IEEE transactions on pattern analysis and machine intelligence • 2018
View 5 Excerpts
Highly Influenced

fewer than 50 Citations

02040201720182019
Citations per Year
Semantic Scholar estimates that this publication has 50 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Weakly Supervised Object Localization with Progressive Domain Adaptation

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 10 Excerpts
Highly Influenced

Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2017
View 3 Excerpts

Deep Residual Learning for Image Recognition

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 1 Excerpt

HCP: A Flexible CNN Framework for Multi-Label Image Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2016
View 9 Excerpts

Reversible Recursive Instance-Level Object Segmentation

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 1 Excerpt

Weakly Supervised Deep Detection Networks

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 1 Excerpt

Detector discovery in the wild: Joint multiple instance and representation learning

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 1 Excerpt

Similar Papers

Loading similar papers…