Weakly Supervised Object Localization Using Size Estimates

@inproceedings{Shi2016WeaklySO,
  title={Weakly Supervised Object Localization Using Size Estimates},
  author={Miaojing Shi and Vittorio Ferrari},
  booktitle={ECCV},
  year={2016}
}
We present a technique for weakly supervised object localization (WSOL), building on the observation that WSOL algorithms usually work better on images with bigger objects. Instead of training the object detector on the entire training set at the same time, we propose a curriculum learning strategy to feed training images into the WSOL learning loop in an order from images containing bigger objects down to smaller ones. To automatically determine the order, we train a regressor to estimate the… CONTINUE READING
Highly Cited
This paper has 30 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 10 times. VIEW TWEETS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 21 extracted citations

Self Paced Deep Learning for Weakly Supervised Object Detection

IEEE transactions on pattern analysis and machine intelligence • 2018
View 10 Excerpts
Highly Influenced

Few-Example Object Detection with Model Communication.

IEEE transactions on pattern analysis and machine intelligence • 2018

SFCM: Learn a Pooling Kernel for Weakly Supervised Object Localization

2018 IEEE International Conference on Multimedia and Expo (ICME) • 2018
View 2 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 50 references

Fast R-CNN

2015 IEEE International Conference on Computer Vision (ICCV) • 2015
View 4 Excerpts
Highly Influenced

Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2017
View 10 Excerpts
Highly Influenced

Weakly supervised object detection with convex clustering

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 7 Excerpts
Highly Influenced

Multi-fold MIL Training for Weakly Supervised Object Localization

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 8 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…