Discriminative learning of deep convolutional feature point descriptors

Edgar Simo-Serra, Eduard Trulls, Luis Ferraz, Iasonas Kokkinos, Pascal Fua, Francesc Moreno-Noguer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

316 Citations (Scopus)

Abstract

Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks (CNNs) to learn discriminant patch representations and in particular train a Siamese network with pairs of (non-)corresponding patches. We deal with the large number of potential pairs with the combination of a stochastic sampling of the training set and an aggressive mining strategy biased towards patches that are hard to classify. By using the L2 distance during both training and testing we develop 128-D descriptors whose euclidean distances reflect patch similarity, and which can be used as a drop-in replacement for any task involving SIFT. We demonstrate consistent performance gains over the state of the art, and generalize well against scaling and rotation, perspective transformation, non-rigid deformation, and illumination changes. Our descriptors are efficient to compute and amenable to modern GPUs, and are publicly available.

Original languageEnglish
Title of host publication2015 International Conference on Computer Vision, ICCV 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages118-126
Number of pages9
ISBN (Electronic)9781467383912
DOIs
Publication statusPublished - 2015 Feb 17
Event15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile
Duration: 2015 Dec 112015 Dec 18

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2015 International Conference on Computer Vision, ICCV 2015
ISSN (Print)1550-5499

Other

Other15th IEEE International Conference on Computer Vision, ICCV 2015
CountryChile
CitySantiago
Period15/12/1115/12/18

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Discriminative learning of deep convolutional feature point descriptors'. Together they form a unique fingerprint.

  • Cite this

    Simo-Serra, E., Trulls, E., Ferraz, L., Kokkinos, I., Fua, P., & Moreno-Noguer, F. (2015). Discriminative learning of deep convolutional feature point descriptors. In 2015 International Conference on Computer Vision, ICCV 2015 (pp. 118-126). [7410379] (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2015 International Conference on Computer Vision, ICCV 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2015.22