---
_id: '2172'
abstract:
- lang: eng
  text: Fisher Kernels and Deep Learning were two developments with significant impact
    on large-scale object categorization in the last years. Both approaches were shown
    to achieve state-of-the-art results on large-scale object categorization datasets,
    such as ImageNet. Conceptually, however, they are perceived as very different
    and it is not uncommon for heated debates to spring up when advocates of both
    paradigms meet at conferences or workshops. In this work, we emphasize the similarities
    between both architectures rather than their differences and we argue that such
    a unified view allows us to transfer ideas from one domain to the other. As a
    concrete example we introduce a method for learning a support vector machine classifier
    with Fisher kernel at the same time as a task-specific data representation. We
    reinterpret the setting as a multi-layer feed forward network. Its final layer
    is the classifier, parameterized by a weight vector, and the two previous layers
    compute Fisher vectors, parameterized by the coefficients of a Gaussian mixture
    model. We introduce a gradient descent based learning algorithm that, in contrast
    to other feature learning techniques, is not just derived from intuition or biological
    analogy, but has a theoretical justification in the framework of statistical learning
    theory. Our experiments show that the new training procedure leads to significant
    improvements in classification accuracy while preserving the modularity and geometric
    interpretability of a support vector machine setup.
article_processing_charge: No
author:
- first_name: Vladyslav
  full_name: Sydorov, Vladyslav
  last_name: Sydorov
- first_name: Mayu
  full_name: Sakurada, Mayu
  last_name: Sakurada
- first_name: Christoph
  full_name: Lampert, Christoph
  id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
  last_name: Lampert
  orcid: 0000-0001-8622-7887
citation:
  ama: 'Sydorov V, Sakurada M, Lampert C. Deep Fisher Kernels – End to end learning
    of the Fisher Kernel GMM parameters. In: <i>Proceedings of the IEEE Computer Society
    Conference on Computer Vision and Pattern Recognition</i>. IEEE; 2014:1402-1409.
    doi:<a href="https://doi.org/10.1109/CVPR.2014.182">10.1109/CVPR.2014.182</a>'
  apa: 'Sydorov, V., Sakurada, M., &#38; Lampert, C. (2014). Deep Fisher Kernels –
    End to end learning of the Fisher Kernel GMM parameters. In <i>Proceedings of
    the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i>
    (pp. 1402–1409). Columbus, USA: IEEE. <a href="https://doi.org/10.1109/CVPR.2014.182">https://doi.org/10.1109/CVPR.2014.182</a>'
  chicago: Sydorov, Vladyslav, Mayu Sakurada, and Christoph Lampert. “Deep Fisher
    Kernels – End to End Learning of the Fisher Kernel GMM Parameters.” In <i>Proceedings
    of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i>,
    1402–9. IEEE, 2014. <a href="https://doi.org/10.1109/CVPR.2014.182">https://doi.org/10.1109/CVPR.2014.182</a>.
  ieee: V. Sydorov, M. Sakurada, and C. Lampert, “Deep Fisher Kernels – End to end
    learning of the Fisher Kernel GMM parameters,” in <i>Proceedings of the IEEE Computer
    Society Conference on Computer Vision and Pattern Recognition</i>, Columbus, USA,
    2014, pp. 1402–1409.
  ista: 'Sydorov V, Sakurada M, Lampert C. 2014. Deep Fisher Kernels – End to end
    learning of the Fisher Kernel GMM parameters. Proceedings of the IEEE Computer
    Society Conference on Computer Vision and Pattern Recognition. CVPR: Computer
    Vision and Pattern Recognition, 1402–1409.'
  mla: Sydorov, Vladyslav, et al. “Deep Fisher Kernels – End to End Learning of the
    Fisher Kernel GMM Parameters.” <i>Proceedings of the IEEE Computer Society Conference
    on Computer Vision and Pattern Recognition</i>, IEEE, 2014, pp. 1402–09, doi:<a
    href="https://doi.org/10.1109/CVPR.2014.182">10.1109/CVPR.2014.182</a>.
  short: V. Sydorov, M. Sakurada, C. Lampert, in:, Proceedings of the IEEE Computer
    Society Conference on Computer Vision and Pattern Recognition, IEEE, 2014, pp.
    1402–1409.
conference:
  end_date: 2014-06-28
  location: Columbus, USA
  name: 'CVPR: Computer Vision and Pattern Recognition'
  start_date: 2014-06-23
corr_author: '1'
date_created: 2018-12-11T11:56:08Z
date_published: 2014-09-24T00:00:00Z
date_updated: 2025-09-29T11:38:10Z
day: '24'
department:
- _id: ChLa
doi: 10.1109/CVPR.2014.182
ec_funded: 1
external_id:
  isi:
  - '000361555601057'
fulldoi: https://doi.org/10.1109/CVPR.2014.182
isi: 1
language:
- iso: eng
month: '09'
oa_version: None
page: 1402 - 1409
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
  call_identifier: FP7
  grant_number: '308036'
  name: Lifelong Learning of Visual Scene Understanding
publication: Proceedings of the IEEE Computer Society Conference on Computer Vision
  and Pattern Recognition
publication_status: published
publisher: IEEE
publist_id: '4812'
quality_controlled: '1'
scopus_import: '1'
status: public
title: Deep Fisher Kernels – End to end learning of the Fisher Kernel GMM parameters
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
year: '2014'
...