Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT

@article{Fischer2014DescriptorMW,
  title={Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT},
  author={Philipp Fischer and Alexey Dosovitskiy and Thomas Brox},
  journal={CoRR},
  year={2014},
  volume={abs/1405.5769}
}
Latest results indicate that features learned via convolutional neural networks outperform previous descriptors on classification tasks by a large margin. It has been shown that these networks still work well when they are applied to datasets or recognition tasks different from those they were trained on. However, descriptors like SIFT are not only used in recognition but also for many correspondence problems that rely on descriptor matching. In this paper we compare features from various… CONTINUE READING
Highly Influential
This paper has highly influenced 19 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 159 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 101 extracted citations

159 Citations

0204020142015201620172018
Citations per Year
Semantic Scholar estimates that this publication has 159 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 18 references

Caffe : An open source convolutional architecture for fast feature embedding

  • Y. Jia
  • Proceedings of the IEEE Conference on Computer…
  • 2013

Caffe: An open source convolutional architecture for fast feature embedding. http: //caffe.berkeleyvision.org

  • Y. Jia
  • 2013
2 Excerpts

Similar Papers

Loading similar papers…