---
_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.
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: Proceedings of the IEEE Computer Society
Conference on Computer Vision and Pattern Recognition. IEEE; 2014:1402-1409.
doi:10.1109/CVPR.2014.182'
apa: 'Sydorov, V., Sakurada, M., & Lampert, C. (2014). Deep Fisher Kernels –
End to end learning of the Fisher Kernel GMM parameters. In Proceedings of
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
(pp. 1402–1409). Columbus, USA: IEEE. https://doi.org/10.1109/CVPR.2014.182'
chicago: Sydorov, Vladyslav, Mayu Sakurada, and Christoph Lampert. “Deep Fisher
Kernels – End to End Learning of the Fisher Kernel GMM Parameters.” In Proceedings
of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition,
1402–9. IEEE, 2014. https://doi.org/10.1109/CVPR.2014.182.
ieee: V. Sydorov, M. Sakurada, and C. Lampert, “Deep Fisher Kernels – End to end
learning of the Fisher Kernel GMM parameters,” in Proceedings of the IEEE Computer
Society Conference on Computer Vision and Pattern Recognition, 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.” Proceedings of the IEEE Computer Society Conference
on Computer Vision and Pattern Recognition, IEEE, 2014, pp. 1402–09, doi:10.1109/CVPR.2014.182.
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
date_created: 2018-12-11T11:56:08Z
date_published: 2014-09-24T00:00:00Z
date_updated: 2021-01-12T06:55:46Z
day: '24'
department:
- _id: ChLa
doi: 10.1109/CVPR.2014.182
ec_funded: 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: 4435EBFC-F248-11E8-B48F-1D18A9856A87
year: '2014'
...