---
_id: '7479'
abstract:
- lang: eng
text: "Multi-exit architectures, in which a stack of processing layers is interleaved
with early output layers, allow the processing of a test example to stop early
and thus save computation time and/or energy. In this work, we propose a new
training procedure for multi-exit architectures based on the principle of knowledge
distillation. The method encourage searly exits to mimic later, more accurate
exits, by matching their output probabilities.\r\nExperiments on CIFAR100 and
\ ImageNet show that distillation-based training significantly improves the
accuracy of early exits while maintaining state-of-the-art accuracy for late
\ ones. The method is particularly beneficial when training data is limited
\ and it allows a straightforward extension to semi-supervised learning,i.e.
making use of unlabeled data at training time. Moreover, it takes only afew lines
to implement and incurs almost no computational overhead at training time, and
none at all at test time."
article_processing_charge: No
author:
- first_name: Phuong
full_name: Bui Thi Mai, Phuong
id: 3EC6EE64-F248-11E8-B48F-1D18A9856A87
last_name: Bui Thi Mai
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Phuong M, Lampert C. Distillation-based training for multi-exit architectures.
In: IEEE International Conference on Computer Vision. Vol 2019-October.
IEEE; 2019:1355-1364. doi:10.1109/ICCV.2019.00144'
apa: 'Phuong, M., & Lampert, C. (2019). Distillation-based training for multi-exit
architectures. In IEEE International Conference on Computer Vision (Vol.
2019–October, pp. 1355–1364). Seoul, Korea: IEEE. https://doi.org/10.1109/ICCV.2019.00144'
chicago: Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit
Architectures.” In IEEE International Conference on Computer Vision, 2019–October:1355–64.
IEEE, 2019. https://doi.org/10.1109/ICCV.2019.00144.
ieee: M. Phuong and C. Lampert, “Distillation-based training for multi-exit architectures,”
in IEEE International Conference on Computer Vision, Seoul, Korea, 2019,
vol. 2019–October, pp. 1355–1364.
ista: 'Phuong M, Lampert C. 2019. Distillation-based training for multi-exit architectures.
IEEE International Conference on Computer Vision. ICCV: International Conference
on Computer Vision vol. 2019–October, 1355–1364.'
mla: Phuong, Mary, and Christoph Lampert. “Distillation-Based Training for Multi-Exit
Architectures.” IEEE International Conference on Computer Vision, vol.
2019–October, IEEE, 2019, pp. 1355–64, doi:10.1109/ICCV.2019.00144.
short: M. Phuong, C. Lampert, in:, IEEE International Conference on Computer Vision,
IEEE, 2019, pp. 1355–1364.
conference:
end_date: 2019-11-02
location: Seoul, Korea
name: 'ICCV: International Conference on Computer Vision'
start_date: 2019-10-27
date_created: 2020-02-11T09:06:57Z
date_published: 2019-10-01T00:00:00Z
date_updated: 2026-07-30T05:33:51Z
day: '01'
ddc:
- '000'
department:
- _id: ChLa
doi: 10.1109/ICCV.2019.00144
ec_funded: 1
external_id:
isi:
- '000531438101047'
file:
- access_level: open_access
checksum: 7b77fb5c2d27c4c37a7612ba46a66117
content_type: application/pdf
creator: bphuong
date_created: 2020-02-11T09:06:39Z
date_updated: 2020-07-14T12:47:59Z
file_id: '7480'
file_name: main.pdf
file_size: 735768
relation: main_file
file_date_updated: 2020-07-14T12:47:59Z
fulldoi: https://doi.org/10.1109/ICCV.2019.00144
has_accepted_license: '1'
isi: 1
language:
- iso: eng
month: '10'
oa: 1
oa_version: Submitted Version
page: 1355-1364
project:
- _id: 2532554C-B435-11E9-9278-68D0E5697425
call_identifier: FP7
grant_number: '308036'
name: Lifelong Learning of Visual Scene Understanding
publication: IEEE International Conference on Computer Vision
publication_identifier:
isbn:
- '9781728148038'
issn:
- 1550-5499
publication_status: published
publisher: IEEE
quality_controlled: '1'
related_material:
record:
- id: '9418'
relation: dissertation_contains
status: public
scopus_import: '1'
status: public
title: Distillation-based training for multi-exit architectures
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 2019-October
year: '2019'
...
---
_id: '18389'
abstract:
- lang: eng
text: This paper explores similarity criteria between non-rigid shapes. Broadly
speaking, such criteria are divided into intrinsic and extrinsic, the first referring
to the metric structure of the objects and the latter to the geometry of the shapes
in the Euclidean space. Both criteria have their advantages and disadvantages;
extrinsic similarity is sensitive to non-rigid deformations of the shapes, while
intrinsic similarity is sensitive to topological noise. Here, we present an approach
unifying both criteria in a single distance. Numerical results demonstrate the
robustness of our approach in cases where using only extrinsic or intrinsic criteria
fail.
article_processing_charge: No
author:
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Michael M.
full_name: Bronstein, Michael M.
last_name: Bronstein
- first_name: Ron
full_name: Kimmel, Ron
last_name: Kimmel
citation:
ama: 'Bronstein AM, Bronstein MM, Kimmel R. Rock, paper, and scissors: Extrinsic
vs. intrinsic similarity of non-rigid shapes. In: 11th International Conference
on Computer Vision. IEEE; 2007. doi:10.1109/iccv.2007.4409076'
apa: 'Bronstein, A. M., Bronstein, M. M., & Kimmel, R. (2007). Rock, paper,
and scissors: Extrinsic vs. intrinsic similarity of non-rigid shapes. In 11th
International Conference on Computer Vision. Rio de Janeiro, Brazil: IEEE.
https://doi.org/10.1109/iccv.2007.4409076'
chicago: 'Bronstein, Alex M., Michael M. Bronstein, and Ron Kimmel. “Rock, Paper,
and Scissors: Extrinsic vs. Intrinsic Similarity of Non-Rigid Shapes.” In 11th
International Conference on Computer Vision. IEEE, 2007. https://doi.org/10.1109/iccv.2007.4409076.'
ieee: 'A. M. Bronstein, M. M. Bronstein, and R. Kimmel, “Rock, paper, and scissors:
Extrinsic vs. intrinsic similarity of non-rigid shapes,” in 11th International
Conference on Computer Vision, Rio de Janeiro, Brazil, 2007.'
ista: 'Bronstein AM, Bronstein MM, Kimmel R. 2007. Rock, paper, and scissors: Extrinsic
vs. intrinsic similarity of non-rigid shapes. 11th International Conference on
Computer Vision. ICCV: International Conference on Computer Vision.'
mla: 'Bronstein, Alex M., et al. “Rock, Paper, and Scissors: Extrinsic vs. Intrinsic
Similarity of Non-Rigid Shapes.” 11th International Conference on Computer
Vision, IEEE, 2007, doi:10.1109/iccv.2007.4409076.'
short: A.M. Bronstein, M.M. Bronstein, R. Kimmel, in:, 11th International Conference
on Computer Vision, IEEE, 2007.
conference:
end_date: 2007-10-21
location: Rio de Janeiro, Brazil
name: 'ICCV: International Conference on Computer Vision'
start_date: 2007-10-14
date_created: 2024-10-15T11:20:54Z
date_published: 2007-10-30T00:00:00Z
date_updated: 2024-11-18T10:12:46Z
day: '30'
doi: 10.1109/iccv.2007.4409076
extern: '1'
fulldoi: https://doi.org/10.1109/iccv.2007.4409076
language:
- iso: eng
month: '10'
oa_version: None
publication: 11th International Conference on Computer Vision
publication_identifier:
isbn:
- '9781424416301'
issn:
- 1550-5499
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Rock, paper, and scissors: Extrinsic vs. intrinsic similarity of non-rigid
shapes'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2007'
...
---
_id: '18390'
abstract:
- lang: eng
text: Symmetry and self-similarity is the cornerstone of Nature, exhibiting itself
through the shapes of natural creations and ubiquitous laws of physics. Since
many natural objects are symmetric, the absence of symmetry can often be an indication
of some anomaly or abnormal behavior. Therefore, detection of asymmetries is important
in numerous practical applications, including crystallography, medical imaging,
and face recognition, to mention a few. Conversely, the assumption of underlying
shape symmetry can facilitate solutions to many problems in shape reconstruction
and analysis. Traditionally, symmetries are described as extrinsic geometric properties
of the shape. While being adequate for rigid shapes, such a description is inappropriate
for non-rigid ones. Extrinsic symmetry can be broken as a result of shape deformations,
while its intrinsic symmetry is preserved. In this paper, we pose the problem
of finding intrinsic symmetries of non-rigid shapes and propose an efficient method
for their computation.
article_processing_charge: No
author:
- first_name: Dan
full_name: Raviv, Dan
last_name: Raviv
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Michael M.
full_name: Bronstein, Michael M.
last_name: Bronstein
- first_name: Ron
full_name: Kimmel, Ron
last_name: Kimmel
citation:
ama: 'Raviv D, Bronstein AM, Bronstein MM, Kimmel R. Symmetries of non-rigid shapes.
In: 11th International Conference on Computer Vision. Vol 72. IEEE; 2007.
doi:10.1109/iccv.2007.4409181'
apa: 'Raviv, D., Bronstein, A. M., Bronstein, M. M., & Kimmel, R. (2007). Symmetries
of non-rigid shapes. In 11th International Conference on Computer Vision
(Vol. 72). Rio de Janeiro, Brazil: IEEE. https://doi.org/10.1109/iccv.2007.4409181'
chicago: Raviv, Dan, Alex M. Bronstein, Michael M. Bronstein, and Ron Kimmel. “Symmetries
of Non-Rigid Shapes.” In 11th International Conference on Computer Vision,
Vol. 72. IEEE, 2007. https://doi.org/10.1109/iccv.2007.4409181.
ieee: D. Raviv, A. M. Bronstein, M. M. Bronstein, and R. Kimmel, “Symmetries of
non-rigid shapes,” in 11th International Conference on Computer Vision,
Rio de Janeiro, Brazil, 2007, vol. 72.
ista: 'Raviv D, Bronstein AM, Bronstein MM, Kimmel R. 2007. Symmetries of non-rigid
shapes. 11th International Conference on Computer Vision. ICCV: International
Conference on Computer Vision vol. 72.'
mla: Raviv, Dan, et al. “Symmetries of Non-Rigid Shapes.” 11th International
Conference on Computer Vision, vol. 72, IEEE, 2007, doi:10.1109/iccv.2007.4409181.
short: D. Raviv, A.M. Bronstein, M.M. Bronstein, R. Kimmel, in:, 11th International
Conference on Computer Vision, IEEE, 2007.
conference:
end_date: 2007-10-21
location: Rio de Janeiro, Brazil
name: 'ICCV: International Conference on Computer Vision'
start_date: 2007-10-14
date_created: 2024-10-15T11:20:54Z
date_published: 2007-12-26T00:00:00Z
date_updated: 2024-11-18T10:07:58Z
day: '26'
doi: 10.1109/iccv.2007.4409181
extern: '1'
fulldoi: https://doi.org/10.1109/iccv.2007.4409181
intvolume: ' 72'
language:
- iso: eng
month: '12'
oa_version: None
publication: 11th International Conference on Computer Vision
publication_identifier:
eissn:
- 2380-7504
isbn:
- '9781424416301'
issn:
- 1550-5499
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Symmetries of non-rigid shapes
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 72
year: '2007'
...
---
OA_type: closed access
_id: '3182'
abstract:
- lang: eng
text: In the work of the authors (2003), we showed that graph cuts can find hypersurfaces
of globally minimal length (or area) under any Riemannian metric. Here we show
that graph cuts on directed regular grids can approximate a significantly more
general class of continuous non-symmetric metrics. Using submodularity condition
(Boros and Hammer, 2002 and Kolmogorov and Zabih, 2004), we obtain a tight characterization
of graph-representable metrics. Such "submodular" metrics have an elegant
geometric interpretation via hypersurface functionals combining length/area and
flux. Practically speaking, we attend 'geo-cuts' algorithm to a wider class of
geometrically motivated hypersurface functionals and show how to globally optimize
any combination of length/area and flux of a given vector field. The concept of
flux was recently introduced into computer vision by Vasilevskiy and Siddiqi (2002)
but it was mainly studied within variational framework so far. We are first to
show that flux can be integrated into graph cuts as well. Combining geometric
concepts of flux and length/area within the global optimization framework of graph
cuts allows principled discrete segmentation models and advances the slate of
the art for the graph cuts methods in vision. In particular we address the "shrinking"
problem of graph cuts, improve segmentation of long thin objects, and introduce
useful shape constraints.
article_processing_charge: No
author:
- first_name: Vladimir
full_name: Kolmogorov, Vladimir
id: 3D50B0BA-F248-11E8-B48F-1D18A9856A87
last_name: Kolmogorov
- first_name: Yuri
full_name: Boykov, Yuri
last_name: Boykov
citation:
ama: 'Kolmogorov V, Boykov Y. What metrics can be approximated by geo cuts or global
optimization of length area and flux. In: Proceedings of the Tenth IEEE International
Conference on Computer Vision Volume 1. Vol 1. IEEE; 2005:564-571. doi:10.1109/ICCV.2005.252'
apa: 'Kolmogorov, V., & Boykov, Y. (2005). What metrics can be approximated
by geo cuts or global optimization of length area and flux. In Proceedings
of the Tenth IEEE International Conference on Computer Vision Volume 1 (Vol.
1, pp. 564–571). NW Washington, DC, United States: IEEE. https://doi.org/10.1109/ICCV.2005.252'
chicago: Kolmogorov, Vladimir, and Yuri Boykov. “What Metrics Can Be Approximated
by Geo Cuts or Global Optimization of Length Area and Flux.” In Proceedings
of the Tenth IEEE International Conference on Computer Vision Volume 1, 1:564–71.
IEEE, 2005. https://doi.org/10.1109/ICCV.2005.252.
ieee: V. Kolmogorov and Y. Boykov, “What metrics can be approximated by geo cuts
or global optimization of length area and flux,” in Proceedings of the Tenth
IEEE International Conference on Computer Vision Volume 1, NW Washington,
DC, United States, 2005, vol. 1, pp. 564–571.
ista: 'Kolmogorov V, Boykov Y. 2005. What metrics can be approximated by geo cuts
or global optimization of length area and flux. Proceedings of the Tenth IEEE
International Conference on Computer Vision Volume 1. ICCV: International Conference
on Computer Vision vol. 1, 564–571.'
mla: Kolmogorov, Vladimir, and Yuri Boykov. “What Metrics Can Be Approximated by
Geo Cuts or Global Optimization of Length Area and Flux.” Proceedings of the
Tenth IEEE International Conference on Computer Vision Volume 1, vol. 1, IEEE,
2005, pp. 564–71, doi:10.1109/ICCV.2005.252.
short: V. Kolmogorov, Y. Boykov, in:, Proceedings of the Tenth IEEE International
Conference on Computer Vision Volume 1, IEEE, 2005, pp. 564–571.
conference:
end_date: 2005-10-20
location: NW Washington, DC, United States
name: 'ICCV: International Conference on Computer Vision'
start_date: 2005-10-17
das_tickbox: '1'
date_created: 2018-12-11T12:01:52Z
date_published: 2005-12-05T00:00:00Z
date_updated: 2026-07-02T08:53:55Z
day: '05'
doi: 10.1109/ICCV.2005.252
extern: '1'
fulldoi: https://doi.org/10.1109/ICCV.2005.252
intvolume: ' 1'
language:
- iso: eng
month: '12'
oa_version: None
page: 564 - 571
publication: Proceedings of the Tenth IEEE International Conference on Computer Vision
Volume 1
publication_identifier:
eissn:
- 2380-7504
issn:
- 1550-5499
publication_status: published
publisher: IEEE
publist_id: '3501'
status: public
title: What metrics can be approximated by geo cuts or global optimization of length
area and flux
type: conference
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 1
year: '2005'
...