Convolutional Neural Networks Learn Compact Local Image Descriptors

  • Christian Osendorfer
  • Justin Bayer
  • Sebastian Urban
  • Patrick van der Smagt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8228)


We investigate if a deep Convolutional Neural Network can learn representations of local image patches that are usable in the important task of keypoint matching. We examine several possible loss functions for this correspondance task and show emprically that a newly suggested loss formulation allows a Convolutional Neural Network to find compact local image descriptors that perform comparably to state-of-the-art approaches.


Convolutional Neural Networks Non-linear Dimensionality Reduction Local Image Descriptor Learning 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  2. 2.
    Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: Proc. CVPR (2008)Google Scholar
  3. 3.
    Brown, M., Hua, G., Winder, S.: Discriminative learning of local image descriptors. Pattern Analysis and Machine Intelligence 33(1), 43–57 (2010)CrossRefGoogle Scholar
  4. 4.
    Trzcinski, T., Christoudias, M., Lepetit, V., Fua, P.: Learning image descriptors with the boosting-trick. In: Proc. NIPS (2012)Google Scholar
  5. 5.
    Simonyan, K., Vedaldi, A., Zisserman, A.: Descriptor learning using convex optimisation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 243–256. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  6. 6.
    Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proc. CVPR (2006)Google Scholar
  7. 7.
    Jarrett, K., Kavukcuoglu, K., Ranzato, M., LeCun, Y.: What is the best multi-stage architecture for object recognition? In: Proc. ICCV (2009)Google Scholar
  8. 8.
    Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: Proc. CVPR (2012)Google Scholar
  9. 9.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Proc. NIPS (2012)Google Scholar
  10. 10.
    Jahrer, M., Grabner, M., Bischof, H.: Learned local descriptors for recognition and matching. In: Computer Vision Winter Workshop (2008)Google Scholar
  11. 11.
    Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: Proc. CVPR (2005)Google Scholar
  12. 12.
    Becker, S., Hinton, G.E.: Self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355(6356), 161–163 (1992)CrossRefGoogle Scholar
  13. 13.
    Bromley, J., Bentz, J.W., Bottou, L., Guyon, I., LeCun, Y., Moore, C., Säckinger, E., Shah, R.: Signature verification using siamese time delay neural network. International Journal of Pattern Recognition and Artificial Intelligence 7(4), 669–688 (1993)CrossRefGoogle Scholar
  14. 14.
    Hadsell, R.: Learning long-range vision for an offroad robot. PhD thesis, New York University (2008)Google Scholar
  15. 15.
    Schulz, H., Behnke, S.: Learning object-class segmentation with convolutional neural networks. In: Proc. ESANN (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Christian Osendorfer
    • 1
  • Justin Bayer
    • 1
  • Sebastian Urban
    • 1
  • Patrick van der Smagt
    • 1
  1. 1.Fakultät für Informatik, Lehrstuhl für Robotik, und EchtzeitsystemeTechnische Universität MünchenMünchen

Personalised recommendations