Introducing Geometry in Active Learning for Image Segmentation

@article{Konyushkova2015IntroducingGI,
  title={Introducing Geometry in Active Learning for Image Segmentation},
  author={Ksenia Konyushkova and Raphael Sznitman and Pascal Fua},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={2974-2982}
}
We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes. To this end, we use these priors not only to select voxels most in need of annotation but to guarantee that they lie on 2D planar patch, which makes it much easier to annotate than if they were randomly distributed in the volume. A simplified version of this approach is effective in natural 2D images. We evaluated our approach on… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 24 CITATIONS

Active Semantic Labeling of Street View Point Clouds

  • 2019 IEEE International Conference on Multimedia and Expo (ICME)
  • 2019
VIEW 2 EXCERPTS
CITES METHODS

Learning to Reduce Annotation Load

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

Spatio-temporal Active Learning for Visual Tracking

Chenfeng Liu, Pengfei Zhu, Qinghua Hu
  • 2019 International Joint Conference on Neural Networks (IJCNN)
  • 2019
VIEW 1 EXCERPT

References

Publications referenced by this paper.
SHOWING 1-10 OF 34 REFERENCES

Active learning for semantic segmentation with expected change

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

A Convex Optimization Framework for Active Learning

  • 2013 IEEE International Conference on Computer Vision
  • 2013
VIEW 3 EXCERPTS

Fast Object Detection with Entropy-Driven Evaluation

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 1 EXCERPT