BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

@article{Dai2015BoxSupEB,
  title={BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation},
  author={Jifeng Dai and Kaiming He and Jian Sun},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={1635-1643}
}
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the performance of deep networks that usually benefit from more training data. In this paper, we propose a method that achieves competitive accuracy but only requires easily obtained bounding box annotations. The basic idea is to iterate between automatically generating… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 267 CITATIONS, ESTIMATED 43% COVERAGE

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 13 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Normalized Cut Loss for Weakly-Supervised CNN Segmentation

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Learning to Segment Human by Watching YouTube

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2017
VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Simple Does It: Weakly Supervised Instance and Semantic Segmentation

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 14 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Scene Understanding using Deep Learning

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 31 Highly Influenced Citations

  • Averaged 72 Citations per year over the last 3 years

  • 16% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Conditional Random Fields as Recurrent Neural Networks

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Multiscale Combinatorial Grouping

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

The Role of Context for Object Detection and Semantic Segmentation in the Wild

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

et al

O. Russakovsky, J. Deng, +7 authors M. Bernstein
  • Imagenet large scale visual recognition challenge. arXiv:1409.0575
  • 2014
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Convolutional feature masking for joint object and stuff segmentation

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Feedforward semantic segmentation with zoom-out features

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…