AnchorNet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching

@article{Novotn2017AnchorNetAW,
  title={AnchorNet: A Weakly Supervised Network to Learn Geometry-Sensitive Features for Semantic Matching},
  author={David Novotn{\'y} and Diane Larlus and Andrea Vedaldi},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={2867-2876}
}
Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of recent deep architectures on the classification task make them unfit for dense correspondence tasks, unless a large amount of supervision is used. In this work, we propose a deep network, termed AnchorNet, that produces image representations that are well-suited… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 25 times over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 11 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 65 references

Similar Papers

Loading similar papers…