---
_id: '14771'
abstract:
- lang: eng
text: Pruning—that is, setting a significant subset of the parameters of a neural
network to zero—is one of the most popular methods of model compression. Yet,
several recent works have raised the issue that pruning may induce or exacerbate
bias in the output of the compressed model. Despite existing evidence for this
phenomenon, the relationship between neural network pruning and induced bias is
not well-understood. In this work, we systematically investigate and characterize
this phenomenon in Convolutional Neural Networks for computer vision. First, we
show that it is in fact possible to obtain highly-sparse models, e.g. with less
than 10% remaining weights, which do not decrease in accuracy nor substantially
increase in bias when compared to dense models. At the same time, we also find
that, at higher sparsities, pruned models exhibit higher uncertainty in their
outputs, as well as increased correlations, which we directly link to increased
bias. We propose easy-to-use criteria which, based only on the uncompressed model,
establish whether bias will increase with pruning, and identify the samples most
susceptible to biased predictions post-compression. Our code can be found at https://github.com/IST-DASLab/pruned-vision-model-bias.
acknowledgement: The authors would like to sincerely thank Sara Hooker for her feedback
during the development of this work. EI was supported in part by the FWF DK VGSCO,
grant agreement number W1260-N35. AP and DA acknowledge generous ERC support, via
Starting Grant 805223 ScaleML.
article_processing_charge: No
arxiv: 1
author:
- first_name: Eugenia B
full_name: Iofinova, Eugenia B
id: f9a17499-f6e0-11ea-865d-fdf9a3f77117
last_name: Iofinova
orcid: 0000-0002-7778-3221
- first_name: Elena-Alexandra
full_name: Peste, Elena-Alexandra
id: 32D78294-F248-11E8-B48F-1D18A9856A87
last_name: Peste
- first_name: Dan-Adrian
full_name: Alistarh, Dan-Adrian
id: 4A899BFC-F248-11E8-B48F-1D18A9856A87
last_name: Alistarh
orcid: 0000-0003-3650-940X
citation:
ama: 'Iofinova EB, Krumes A, Alistarh D-A. Bias in pruned vision models: In-depth
analysis and countermeasures. In: 2023 IEEE/CVF Conference on Computer Vision
and Pattern Recognition. IEEE; 2023:24364-24373. doi:10.1109/cvpr52729.2023.02334'
apa: 'Iofinova, E. B., Krumes, A., & Alistarh, D.-A. (2023). Bias in pruned
vision models: In-depth analysis and countermeasures. In 2023 IEEE/CVF Conference
on Computer Vision and Pattern Recognition (pp. 24364–24373). Vancouver, BC,
Canada: IEEE. https://doi.org/10.1109/cvpr52729.2023.02334'
chicago: 'Iofinova, Eugenia B, Alexandra Krumes, and Dan-Adrian Alistarh. “Bias
in Pruned Vision Models: In-Depth Analysis and Countermeasures.” In 2023 IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 24364–73. IEEE, 2023.
https://doi.org/10.1109/cvpr52729.2023.02334.'
ieee: 'E. B. Iofinova, A. Krumes, and D.-A. Alistarh, “Bias in pruned vision models:
In-depth analysis and countermeasures,” in 2023 IEEE/CVF Conference on Computer
Vision and Pattern Recognition, Vancouver, BC, Canada, 2023, pp. 24364–24373.'
ista: 'Iofinova EB, Krumes A, Alistarh D-A. 2023. Bias in pruned vision models:
In-depth analysis and countermeasures. 2023 IEEE/CVF Conference on Computer Vision
and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition,
24364–24373.'
mla: 'Iofinova, Eugenia B., et al. “Bias in Pruned Vision Models: In-Depth Analysis
and Countermeasures.” 2023 IEEE/CVF Conference on Computer Vision and Pattern
Recognition, IEEE, 2023, pp. 24364–73, doi:10.1109/cvpr52729.2023.02334.'
short: E.B. Iofinova, A. Krumes, D.-A. Alistarh, in:, 2023 IEEE/CVF Conference on
Computer Vision and Pattern Recognition, IEEE, 2023, pp. 24364–24373.
conference:
end_date: 2023-06-24
location: Vancouver, BC, Canada
name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
start_date: 2023-06-17
corr_author: '1'
date_created: 2024-01-10T08:42:40Z
date_published: 2023-08-22T00:00:00Z
date_updated: 2026-05-19T11:20:27Z
day: '22'
department:
- _id: DaAl
- _id: ChLa
doi: 10.1109/cvpr52729.2023.02334
ec_funded: 1
external_id:
arxiv:
- '2304.12622'
isi:
- '001062531308068'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2304.12622
month: '08'
oa: 1
oa_version: Preprint
page: 24364-24373
project:
- _id: 9B9290DE-BA93-11EA-9121-9846C619BF3A
grant_number: W1260-N35
name: Vienna Graduate School on Computational Optimization
- _id: 268A44D6-B435-11E9-9278-68D0E5697425
call_identifier: H2020
grant_number: '805223'
name: Elastic Coordination for Scalable Machine Learning
publication: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eisbn:
- '9798350301298'
eissn:
- 2575-7075
publication_status: published
publisher: IEEE
quality_controlled: '1'
related_material:
link:
- relation: software
url: https://github.com/IST-DASLab/pruned-vision-model-bias
record:
- id: '21854'
relation: dissertation_contains
status: public
status: public
title: 'Bias in pruned vision models: In-depth analysis and countermeasures'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2023'
...
---
_id: '12299'
abstract:
- lang: eng
text: 'Transfer learning is a classic paradigm by which models pretrained on large
“upstream” datasets are adapted to yield good results on “downstream” specialized
datasets. Generally, more accurate models on the “upstream” dataset tend to provide
better transfer accuracy “downstream”. In this work, we perform an in-depth investigation
of this phenomenon in the context of convolutional neural networks (CNNs) trained
on the ImageNet dataset, which have been pruned-that is, compressed by sparsifiying
their connections. We consider transfer using unstructured pruned models obtained
by applying several state-of-the-art pruning methods, including magnitude-based,
second-order, regrowth, lottery-ticket, and regularization approaches, in the
context of twelve standard transfer tasks. In a nutshell, our study shows that
sparse models can match or even outperform the transfer performance of dense models,
even at high sparsities, and, while doing so, can lead to significant inference
and even training speedups. At the same time, we observe and analyze significant
differences in the behaviour of different pruning methods. The code is available
at: https://github.com/IST-DASLab/sparse-imagenet-transfer.'
acknowledgement: he authors would like to sincerely thank Christoph Lampert and Nir
Shavit for fruitful discussions during the development of this work, and Eldar Kurtic
for experimental support. EI was supported in part by the FWF DK VGSCO, grant agreement
number W1260-N35, while AP and DA acknowledge generous support by the ERC, via Starting
Grant 805223 ScaleML.
article_processing_charge: No
arxiv: 1
author:
- first_name: Eugenia B
full_name: Iofinova, Eugenia B
id: f9a17499-f6e0-11ea-865d-fdf9a3f77117
last_name: Iofinova
orcid: 0000-0002-7778-3221
- first_name: Elena-Alexandra
full_name: Peste, Elena-Alexandra
id: 32D78294-F248-11E8-B48F-1D18A9856A87
last_name: Peste
- first_name: Mark
full_name: Kurtz, Mark
last_name: Kurtz
- first_name: Dan-Adrian
full_name: Alistarh, Dan-Adrian
id: 4A899BFC-F248-11E8-B48F-1D18A9856A87
last_name: Alistarh
orcid: 0000-0003-3650-940X
citation:
ama: 'Iofinova EB, Krumes A, Kurtz M, Alistarh D-A. How well do sparse ImageNet
models transfer? In: 2022 IEEE/CVF Conference on Computer Vision and Pattern
Recognition. Institute of Electrical and Electronics Engineers; 2022:12256-12266.
doi:10.1109/cvpr52688.2022.01195'
apa: 'Iofinova, E. B., Krumes, A., Kurtz, M., & Alistarh, D.-A. (2022). How
well do sparse ImageNet models transfer? In 2022 IEEE/CVF Conference on Computer
Vision and Pattern Recognition (pp. 12256–12266). New Orleans, LA, United
States: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/cvpr52688.2022.01195'
chicago: Iofinova, Eugenia B, Alexandra Krumes, Mark Kurtz, and Dan-Adrian Alistarh.
“How Well Do Sparse ImageNet Models Transfer?” In 2022 IEEE/CVF Conference
on Computer Vision and Pattern Recognition, 12256–66. Institute of Electrical
and Electronics Engineers, 2022. https://doi.org/10.1109/cvpr52688.2022.01195.
ieee: E. B. Iofinova, A. Krumes, M. Kurtz, and D.-A. Alistarh, “How well do sparse
ImageNet models transfer?,” in 2022 IEEE/CVF Conference on Computer Vision
and Pattern Recognition, New Orleans, LA, United States, 2022, pp. 12256–12266.
ista: 'Iofinova EB, Krumes A, Kurtz M, Alistarh D-A. 2022. How well do sparse ImageNet
models transfer? 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.
CVPR: Computer Vision and Pattern Recognition, 12256–12266.'
mla: Iofinova, Eugenia B., et al. “How Well Do Sparse ImageNet Models Transfer?”
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute
of Electrical and Electronics Engineers, 2022, pp. 12256–66, doi:10.1109/cvpr52688.2022.01195.
short: E.B. Iofinova, A. Krumes, M. Kurtz, D.-A. Alistarh, in:, 2022 IEEE/CVF Conference
on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics
Engineers, 2022, pp. 12256–12266.
conference:
end_date: 2022-06-24
location: New Orleans, LA, United States
name: 'CVPR: Computer Vision and Pattern Recognition'
start_date: 2022-06-18
corr_author: '1'
date_created: 2023-01-16T10:06:00Z
date_published: 2022-09-27T00:00:00Z
date_updated: 2026-04-07T13:30:19Z
day: '27'
department:
- _id: DaAl
- _id: ChLa
doi: 10.1109/cvpr52688.2022.01195
ec_funded: 1
external_id:
arxiv:
- '2111.13445'
isi:
- '000870759105034'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.2111.13445
month: '09'
oa: 1
oa_version: Preprint
page: 12256-12266
project:
- _id: 9B9290DE-BA93-11EA-9121-9846C619BF3A
grant_number: W1260-N35
name: Vienna Graduate School on Computational Optimization
- _id: 268A44D6-B435-11E9-9278-68D0E5697425
call_identifier: H2020
grant_number: '805223'
name: Elastic Coordination for Scalable Machine Learning
publication: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eissn:
- 2575-7075
publication_status: published
publisher: Institute of Electrical and Electronics Engineers
quality_controlled: '1'
related_material:
record:
- id: '13074'
relation: dissertation_contains
status: public
scopus_import: '1'
status: public
title: How well do sparse ImageNet models transfer?
type: conference
user_id: 4359f0d1-fa6c-11eb-b949-802e58b17ae8
year: '2022'
...
---
_id: '14114'
abstract:
- lang: eng
text: Algorithmic fairness is frequently motivated in terms of a trade-off in which
overall performance is decreased so as to improve performance on disadvantaged
groups where the algorithm would otherwise be less accurate. Contrary to this,
we find that applying existing fairness approaches to computer vision improve
fairness by degrading the performance of classifiers across all groups (with increased
degradation on the best performing groups). Extending the bias-variance decomposition
for classification to fairness, we theoretically explain why the majority of fairness
methods designed for low capacity models should not be used in settings involving
high-capacity models, a scenario common to computer vision. We corroborate this
analysis with extensive experimental support that shows that many of the fairness
heuristics used in computer vision also degrade performance on the most disadvantaged
groups. Building on these insights, we propose an adaptive augmentation strategy
that, uniquely, of all methods tested, improves performance for the disadvantaged
groups.
article_processing_charge: No
arxiv: 1
author:
- first_name: Dominik
full_name: Zietlow, Dominik
last_name: Zietlow
- first_name: Michael
full_name: Lohaus, Michael
last_name: Lohaus
- first_name: Guha
full_name: Balakrishnan, Guha
last_name: Balakrishnan
- first_name: Matthaus
full_name: Kleindessner, Matthaus
last_name: Kleindessner
- first_name: Francesco
full_name: Locatello, Francesco
id: 26cfd52f-2483-11ee-8040-88983bcc06d4
last_name: Locatello
orcid: 0000-0002-4850-0683
- first_name: Bernhard
full_name: Scholkopf, Bernhard
last_name: Scholkopf
- first_name: Chris
full_name: Russell, Chris
last_name: Russell
citation:
ama: 'Zietlow D, Lohaus M, Balakrishnan G, et al. Leveling down in computer vision:
Pareto inefficiencies in fair deep classifiers. In: 2022 IEEE/CVF Conference
on Computer Vision and Pattern Recognition. Institute of Electrical and Electronics
Engineers; 2022:10400-10411. doi:10.1109/cvpr52688.2022.01016'
apa: 'Zietlow, D., Lohaus, M., Balakrishnan, G., Kleindessner, M., Locatello, F.,
Scholkopf, B., & Russell, C. (2022). Leveling down in computer vision: Pareto
inefficiencies in fair deep classifiers. In 2022 IEEE/CVF Conference on Computer
Vision and Pattern Recognition (pp. 10400–10411). New Orleans, LA, United
States: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/cvpr52688.2022.01016'
chicago: 'Zietlow, Dominik, Michael Lohaus, Guha Balakrishnan, Matthaus Kleindessner,
Francesco Locatello, Bernhard Scholkopf, and Chris Russell. “Leveling down in
Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers.” In 2022 IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 10400–411. Institute
of Electrical and Electronics Engineers, 2022. https://doi.org/10.1109/cvpr52688.2022.01016.'
ieee: 'D. Zietlow et al., “Leveling down in computer vision: Pareto inefficiencies
in fair deep classifiers,” in 2022 IEEE/CVF Conference on Computer Vision and
Pattern Recognition, New Orleans, LA, United States, 2022, pp. 10400–10411.'
ista: 'Zietlow D, Lohaus M, Balakrishnan G, Kleindessner M, Locatello F, Scholkopf
B, Russell C. 2022. Leveling down in computer vision: Pareto inefficiencies in
fair deep classifiers. 2022 IEEE/CVF Conference on Computer Vision and Pattern
Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 10400–10411.'
mla: 'Zietlow, Dominik, et al. “Leveling down in Computer Vision: Pareto Inefficiencies
in Fair Deep Classifiers.” 2022 IEEE/CVF Conference on Computer Vision and
Pattern Recognition, Institute of Electrical and Electronics Engineers, 2022,
pp. 10400–11, doi:10.1109/cvpr52688.2022.01016.'
short: D. Zietlow, M. Lohaus, G. Balakrishnan, M. Kleindessner, F. Locatello, B.
Scholkopf, C. Russell, in:, 2022 IEEE/CVF Conference on Computer Vision and Pattern
Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 10400–10411.
conference:
end_date: 2022-06-24
location: New Orleans, LA, United States
name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
start_date: 2022-06-18
date_created: 2023-08-21T12:18:00Z
date_published: 2022-07-01T00:00:00Z
date_updated: 2023-09-11T09:19:14Z
day: '01'
department:
- _id: FrLo
doi: 10.1109/cvpr52688.2022.01016
extern: '1'
external_id:
arxiv:
- '2203.04913'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2203.04913
month: '07'
oa: 1
oa_version: Preprint
page: 10400-10411
publication: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eissn:
- 2575-7075
isbn:
- '9781665469470'
issn:
- 1063-6919
publication_status: published
publisher: Institute of Electrical and Electronics Engineers
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers'
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2022'
...
---
_id: '18258'
abstract:
- lang: eng
text: Distance metric learning (DML) has been successfully applied to object classification,
both in the standard regime of rich training data and in the few-shot scenario,
where each category is represented by only a few examples. In this work, we propose
a new method for DML that simultaneously learns the backbone network parameters,
the embedding space, and the multi-modal distribution of each of the training
categories in that space, in a single end-to-end training process. Our approach
outperforms state-of-the-art methods for DML-based object classification on a
variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness
of our approach on the problem of few-shot object detection, by incorporating
the proposed DML architecture as a classification head into a standard object
detection model. We achieve the best results on the ImageNet-LOC dataset compared
to strong baselines, when only a few training examples are available. We also
offer the community a new episodic benchmark based on the ImageNet dataset for
the few-shot object detection task.
article_number: '8953439'
article_processing_charge: No
author:
- first_name: Leonid
full_name: Karlinsky, Leonid
last_name: Karlinsky
- first_name: Joseph
full_name: Shtok, Joseph
last_name: Shtok
- first_name: Sivan
full_name: Harary, Sivan
last_name: Harary
- first_name: Eli
full_name: Schwartz, Eli
last_name: Schwartz
- first_name: Amit
full_name: Aides, Amit
last_name: Aides
- first_name: Rogerio
full_name: Feris, Rogerio
last_name: Feris
- first_name: Raja
full_name: Giryes, Raja
last_name: Giryes
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
citation:
ama: 'Karlinsky L, Shtok J, Harary S, et al. Repmet: Representative-based metric
learning for classification and few-shot object detection. In: 2019 IEEE/CVF
Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2020.
doi:10.1109/cvpr.2019.00534'
apa: 'Karlinsky, L., Shtok, J., Harary, S., Schwartz, E., Aides, A., Feris, R.,
… Bronstein, A. M. (2020). Repmet: Representative-based metric learning for classification
and few-shot object detection. In 2019 IEEE/CVF Conference on Computer Vision
and Pattern Recognition (CVPR). Long Beach, CA, United States: IEEE. https://doi.org/10.1109/cvpr.2019.00534'
chicago: 'Karlinsky, Leonid, Joseph Shtok, Sivan Harary, Eli Schwartz, Amit Aides,
Rogerio Feris, Raja Giryes, and Alex M. Bronstein. “Repmet: Representative-Based
Metric Learning for Classification and Few-Shot Object Detection.” In 2019
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE,
2020. https://doi.org/10.1109/cvpr.2019.00534.'
ieee: 'L. Karlinsky et al., “Repmet: Representative-based metric learning
for classification and few-shot object detection,” in 2019 IEEE/CVF Conference
on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, United
States, 2020.'
ista: 'Karlinsky L, Shtok J, Harary S, Schwartz E, Aides A, Feris R, Giryes R, Bronstein
AM. 2020. Repmet: Representative-based metric learning for classification and
few-shot object detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern
Recognition (CVPR). 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition,
8953439.'
mla: 'Karlinsky, Leonid, et al. “Repmet: Representative-Based Metric Learning for
Classification and Few-Shot Object Detection.” 2019 IEEE/CVF Conference on
Computer Vision and Pattern Recognition (CVPR), 8953439, IEEE, 2020, doi:10.1109/cvpr.2019.00534.'
short: L. Karlinsky, J. Shtok, S. Harary, E. Schwartz, A. Aides, R. Feris, R. Giryes,
A.M. Bronstein, in:, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
(CVPR), IEEE, 2020.
conference:
end_date: 2019-06-20
location: Long Beach, CA, United States
name: 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition
start_date: 2019-06-15
date_created: 2024-10-08T13:08:09Z
date_published: 2020-01-09T00:00:00Z
date_updated: 2024-12-05T15:38:16Z
day: '09'
doi: 10.1109/cvpr.2019.00534
extern: '1'
language:
- iso: eng
month: '01'
oa_version: None
publication: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
publication_identifier:
eissn:
- 2575-7075
isbn:
- '9781728132945'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Repmet: Representative-based metric learning for classification and few-shot
object detection'
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2020'
...
---
_id: '18259'
abstract:
- lang: eng
text: Example synthesis is one of the leading methods to tackle the problem of few-shot
learning, where only a small number of samples per class are available. However,
current synthesis approaches only address the scenario of a single category label
per image. In this work, we propose a novel technique for synthesizing samples
with multiple labels for the (yet unhandled) multi-label few-shot classification
scenario. We propose to combine pairs of given examples in feature space, so that
the resulting synthesized feature vectors will correspond to examples whose label
sets are obtained through certain set operations on the label sets of the corresponding
input pairs. Thus, our method is capable of producing a sample containing the
intersection, union or set-difference of labels present in two input samples.
As we show, these set operations generalize to labels unseen during training.
This enables performing augmentation on examples of novel categories, thus, facilitating
multi-label few-shot classifier learning. We conduct numerous experiments showing
promising results for the label-set manipulation capabilities of the proposed
approach, both directly (using the classification and retrieval metrics), and
in the context of performing data augmentation for multi-label few-shot learning.
We propose a benchmark for this new and challenging task and show that our method
compares favorably to all the common baselines.
article_number: '8954088'
article_processing_charge: No
arxiv: 1
author:
- first_name: Amit
full_name: Alfassy, Amit
last_name: Alfassy
- first_name: Leonid
full_name: Karlinsky, Leonid
last_name: Karlinsky
- first_name: Amit
full_name: Aides, Amit
last_name: Aides
- first_name: Joseph
full_name: Shtok, Joseph
last_name: Shtok
- first_name: Sivan
full_name: Harary, Sivan
last_name: Harary
- first_name: Rogerio
full_name: Feris, Rogerio
last_name: Feris
- first_name: Raja
full_name: Giryes, Raja
last_name: Giryes
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
citation:
ama: 'Alfassy A, Karlinsky L, Aides A, et al. Laso: Label-set operations networks
for multi-label few-shot learning. In: 2019 IEEE/CVF Conference on Computer
Vision and Pattern Recognition (CVPR). IEEE; 2020. doi:10.1109/cvpr.2019.00671'
apa: 'Alfassy, A., Karlinsky, L., Aides, A., Shtok, J., Harary, S., Feris, R., …
Bronstein, A. M. (2020). Laso: Label-set operations networks for multi-label few-shot
learning. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
(CVPR). Long Beach, CA, United States: IEEE. https://doi.org/10.1109/cvpr.2019.00671'
chicago: 'Alfassy, Amit, Leonid Karlinsky, Amit Aides, Joseph Shtok, Sivan Harary,
Rogerio Feris, Raja Giryes, and Alex M. Bronstein. “Laso: Label-Set Operations
Networks for Multi-Label Few-Shot Learning.” In 2019 IEEE/CVF Conference on
Computer Vision and Pattern Recognition (CVPR). IEEE, 2020. https://doi.org/10.1109/cvpr.2019.00671.'
ieee: 'A. Alfassy et al., “Laso: Label-set operations networks for multi-label
few-shot learning,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern
Recognition (CVPR), Long Beach, CA, United States, 2020.'
ista: 'Alfassy A, Karlinsky L, Aides A, Shtok J, Harary S, Feris R, Giryes R, Bronstein
AM. 2020. Laso: Label-set operations networks for multi-label few-shot learning.
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 32nd
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8954088.'
mla: 'Alfassy, Amit, et al. “Laso: Label-Set Operations Networks for Multi-Label
Few-Shot Learning.” 2019 IEEE/CVF Conference on Computer Vision and Pattern
Recognition (CVPR), 8954088, IEEE, 2020, doi:10.1109/cvpr.2019.00671.'
short: A. Alfassy, L. Karlinsky, A. Aides, J. Shtok, S. Harary, R. Feris, R. Giryes,
A.M. Bronstein, in:, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
(CVPR), IEEE, 2020.
conference:
end_date: 2019-06-20
location: Long Beach, CA, United States
name: 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition
start_date: 2019-06-15
date_created: 2024-10-08T13:08:26Z
date_published: 2020-01-09T00:00:00Z
date_updated: 2024-12-05T15:33:21Z
day: '09'
doi: 10.1109/cvpr.2019.00671
extern: '1'
external_id:
arxiv:
- '1902.09811'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.1902.09811
month: '01'
oa: 1
oa_version: Preprint
publication: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
publication_identifier:
eissn:
- 2575-7075
isbn:
- '9781728132945'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Laso: Label-set operations networks for multi-label few-shot learning'
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2020'
...
---
_id: '18260'
abstract:
- lang: eng
text: We introduce the first completely unsupervised correspondence learning approach
for deformable 3D shapes. Key to our model is the understanding that natural deformations
(such as changes in pose) approximately preserve the metric structure of the surface,
yielding a natural criterion to drive the learning process toward distortion-minimizing
predictions. On this basis, we overcome the need for annotated data and replace
it by a purely geometric criterion. The resulting learning model is class-agnostic,
and is able to leverage any type of deformable geometric data for the training
phase. In contrast to existing supervised approaches which specialize on the class
seen at training time, we demonstrate stronger generalization as well as applicability
to a variety of challenging settings. We showcase our method on a wide selection
of correspondence benchmarks, where we outperform other methods in terms of accuracy,
generalization, and efficiency.
article_number: '8953366'
article_processing_charge: No
author:
- first_name: Oshri
full_name: Halimi, Oshri
last_name: Halimi
- first_name: Or
full_name: Litany, Or
last_name: Litany
- first_name: Emanuele Rodola
full_name: Rodola, Emanuele Rodola
last_name: Rodola
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Ron
full_name: Kimmel, Ron
last_name: Kimmel
citation:
ama: 'Halimi O, Litany O, Rodola ER, Bronstein AM, Kimmel R. Unsupervised learning
of dense shape correspondence. In: 2019 IEEE/CVF Conference on Computer Vision
and Pattern Recognition (CVPR). IEEE; 2020. doi:10.1109/cvpr.2019.00450'
apa: 'Halimi, O., Litany, O., Rodola, E. R., Bronstein, A. M., & Kimmel, R.
(2020). Unsupervised learning of dense shape correspondence. In 2019 IEEE/CVF
Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach,
CA, United States: IEEE. https://doi.org/10.1109/cvpr.2019.00450'
chicago: Halimi, Oshri, Or Litany, Emanuele Rodola Rodola, Alex M. Bronstein, and
Ron Kimmel. “Unsupervised Learning of Dense Shape Correspondence.” In 2019
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE,
2020. https://doi.org/10.1109/cvpr.2019.00450.
ieee: O. Halimi, O. Litany, E. R. Rodola, A. M. Bronstein, and R. Kimmel, “Unsupervised
learning of dense shape correspondence,” in 2019 IEEE/CVF Conference on Computer
Vision and Pattern Recognition (CVPR), Long Beach, CA, United States, 2020.
ista: Halimi O, Litany O, Rodola ER, Bronstein AM, Kimmel R. 2020. Unsupervised
learning of dense shape correspondence. 2019 IEEE/CVF Conference on Computer Vision
and Pattern Recognition (CVPR). 32nd IEEE/CVF Conference on Computer Vision and
Pattern Recognition, 8953366.
mla: Halimi, Oshri, et al. “Unsupervised Learning of Dense Shape Correspondence.”
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),
8953366, IEEE, 2020, doi:10.1109/cvpr.2019.00450.
short: O. Halimi, O. Litany, E.R. Rodola, A.M. Bronstein, R. Kimmel, in:, 2019 IEEE/CVF
Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2020.
conference:
end_date: 2019-06-20
location: Long Beach, CA, United States
name: 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition
start_date: 2019-06-15
date_created: 2024-10-08T13:08:43Z
date_published: 2020-01-09T00:00:00Z
date_updated: 2024-12-05T15:19:01Z
day: '09'
doi: 10.1109/cvpr.2019.00450
extern: '1'
language:
- iso: eng
month: '01'
oa_version: None
publication: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
publication_identifier:
eissn:
- 2575-7075
isbn:
- '9781728132945'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Unsupervised learning of dense shape correspondence
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2020'
...
---
_id: '8186'
abstract:
- lang: eng
text: "Numerous methods have been proposed for probabilistic generative modelling
of\r\n3D objects. However, none of these is able to produce textured objects,
which\r\nrenders them of limited use for practical tasks. In this work, we present
the\r\nfirst generative model of textured 3D meshes. Training such a model would\r\ntraditionally
require a large dataset of textured meshes, but unfortunately,\r\nexisting datasets
of meshes lack detailed textures. We instead propose a new\r\ntraining methodology
that allows learning from collections of 2D images without\r\nany 3D information.
To do so, we train our model to explain a distribution of\r\nimages by modelling
each image as a 3D foreground object placed in front of a\r\n2D background. Thus,
it learns to generate meshes that when rendered, produce\r\nimages similar to
those in its training set.\r\n A well-known problem when generating meshes with
deep networks is the\r\nemergence of self-intersections, which are problematic
for many use-cases. As a\r\nsecond contribution we therefore introduce a new generation
process for 3D\r\nmeshes that guarantees no self-intersections arise, based on
the physical\r\nintuition that faces should push one another out of the way as
they move.\r\n We conduct extensive experiments on our approach, reporting quantitative
and\r\nqualitative results on both synthetic data and natural images. These show
our\r\nmethod successfully learns to generate plausible and diverse textured 3D\r\nsamples
for five challenging object classes."
article_processing_charge: No
arxiv: 1
author:
- first_name: Paul M
full_name: Henderson, Paul M
id: 13C09E74-18D9-11E9-8878-32CFE5697425
last_name: Henderson
orcid: 0000-0002-5198-7445
- first_name: Vagia
full_name: Tsiminaki, Vagia
last_name: Tsiminaki
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
citation:
ama: 'Henderson PM, Tsiminaki V, Lampert C. Leveraging 2D data to learn textured
3D mesh generation. In: Proceedings of the IEEE/CVF Conference on Computer
Vision and Pattern Recognition. IEEE; 2020:7498-7507. doi:10.1109/CVPR42600.2020.00752'
apa: 'Henderson, P. M., Tsiminaki, V., & Lampert, C. (2020). Leveraging 2D data
to learn textured 3D mesh generation. In Proceedings of the IEEE/CVF Conference
on Computer Vision and Pattern Recognition (pp. 7498–7507). Virtual: IEEE.
https://doi.org/10.1109/CVPR42600.2020.00752'
chicago: Henderson, Paul M, Vagia Tsiminaki, and Christoph Lampert. “Leveraging
2D Data to Learn Textured 3D Mesh Generation.” In Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 7498–7507. IEEE, 2020.
https://doi.org/10.1109/CVPR42600.2020.00752.
ieee: P. M. Henderson, V. Tsiminaki, and C. Lampert, “Leveraging 2D data to learn
textured 3D mesh generation,” in Proceedings of the IEEE/CVF Conference on
Computer Vision and Pattern Recognition, Virtual, 2020, pp. 7498–7507.
ista: 'Henderson PM, Tsiminaki V, Lampert C. 2020. Leveraging 2D data to learn textured
3D mesh generation. Proceedings of the IEEE/CVF Conference on Computer Vision
and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition,
7498–7507.'
mla: Henderson, Paul M., et al. “Leveraging 2D Data to Learn Textured 3D Mesh Generation.”
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,
IEEE, 2020, pp. 7498–507, doi:10.1109/CVPR42600.2020.00752.
short: P.M. Henderson, V. Tsiminaki, C. Lampert, in:, Proceedings of the IEEE/CVF
Conference on Computer Vision and Pattern Recognition, IEEE, 2020, pp. 7498–7507.
conference:
end_date: 2020-06-19
location: Virtual
name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
start_date: 2020-06-14
date_created: 2020-07-31T16:53:49Z
date_published: 2020-07-01T00:00:00Z
date_updated: 2023-10-17T07:37:11Z
day: '01'
ddc:
- '004'
department:
- _id: ChLa
doi: 10.1109/CVPR42600.2020.00752
external_id:
arxiv:
- '2004.04180'
file:
- access_level: open_access
content_type: application/pdf
creator: phenders
date_created: 2020-07-31T16:57:12Z
date_updated: 2020-07-31T16:57:12Z
file_id: '8187'
file_name: paper.pdf
file_size: 10262773
relation: main_file
success: 1
file_date_updated: 2020-07-31T16:57:12Z
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://openaccess.thecvf.com/content_CVPR_2020/papers/Henderson_Leveraging_2D_Data_to_Learn_Textured_3D_Mesh_Generation_CVPR_2020_paper.pdf
month: '07'
oa: 1
oa_version: Submitted Version
page: 7498-7507
publication: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern
Recognition
publication_identifier:
eisbn:
- '9781728171685'
eissn:
- 2575-7075
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Leveraging 2D data to learn textured 3D mesh generation
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2020'
...
---
_id: '10882'
abstract:
- lang: eng
text: 'We introduce Intelligent Annotation Dialogs for bounding box annotation.
We train an agent to automatically choose a sequence of actions for a human annotator
to produce a bounding box in a minimal amount of time. Specifically, we consider
two actions: box verification [34], where the annotator verifies a box generated
by an object detector, and manual box drawing. We explore two kinds of agents,
one based on predicting the probability that a box will be positively verified,
and the other based on reinforcement learning. We demonstrate that (1) our agents
are able to learn efficient annotation strategies in several scenarios, automatically
adapting to the image difficulty, the desired quality of the boxes, and the detector
strength; (2) in all scenarios the resulting annotation dialogs speed up annotation
compared to manual box drawing alone and box verification alone, while also outperforming
any fixed combination of verification and drawing in most scenarios; (3) in a
realistic scenario where the detector is iteratively re-trained, our agents evolve
a series of strategies that reflect the shifting trade-off between verification
and drawing as the detector grows stronger.'
article_processing_charge: No
arxiv: 1
author:
- first_name: Jasper
full_name: Uijlings, Jasper
last_name: Uijlings
- first_name: Ksenia
full_name: Konyushkova, Ksenia
last_name: Konyushkova
- first_name: Christoph
full_name: Lampert, Christoph
id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
last_name: Lampert
orcid: 0000-0001-8622-7887
- first_name: Vittorio
full_name: Ferrari, Vittorio
last_name: Ferrari
citation:
ama: 'Uijlings J, Konyushkova K, Lampert C, Ferrari V. Learning intelligent dialogs
for bounding box annotation. In: 2018 IEEE/CVF Conference on Computer Vision
and Pattern Recognition. IEEE; 2018:9175-9184. doi:10.1109/cvpr.2018.00956'
apa: 'Uijlings, J., Konyushkova, K., Lampert, C., & Ferrari, V. (2018). Learning
intelligent dialogs for bounding box annotation. In 2018 IEEE/CVF Conference
on Computer Vision and Pattern Recognition (pp. 9175–9184). Salt Lake City,
UT, United States: IEEE. https://doi.org/10.1109/cvpr.2018.00956'
chicago: Uijlings, Jasper, Ksenia Konyushkova, Christoph Lampert, and Vittorio Ferrari.
“Learning Intelligent Dialogs for Bounding Box Annotation.” In 2018 IEEE/CVF
Conference on Computer Vision and Pattern Recognition, 9175–84. IEEE, 2018.
https://doi.org/10.1109/cvpr.2018.00956.
ieee: J. Uijlings, K. Konyushkova, C. Lampert, and V. Ferrari, “Learning intelligent
dialogs for bounding box annotation,” in 2018 IEEE/CVF Conference on Computer
Vision and Pattern Recognition, Salt Lake City, UT, United States, 2018, pp.
9175–9184.
ista: 'Uijlings J, Konyushkova K, Lampert C, Ferrari V. 2018. Learning intelligent
dialogs for bounding box annotation. 2018 IEEE/CVF Conference on Computer Vision
and Pattern Recognition. CVF: Conference on Computer Vision and Pattern Recognition,
9175–9184.'
mla: Uijlings, Jasper, et al. “Learning Intelligent Dialogs for Bounding Box Annotation.”
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE,
2018, pp. 9175–84, doi:10.1109/cvpr.2018.00956.
short: J. Uijlings, K. Konyushkova, C. Lampert, V. Ferrari, in:, 2018 IEEE/CVF Conference
on Computer Vision and Pattern Recognition, IEEE, 2018, pp. 9175–9184.
conference:
end_date: 2018-06-23
location: Salt Lake City, UT, United States
name: 'CVF: Conference on Computer Vision and Pattern Recognition'
start_date: 2018-06-18
corr_author: '1'
date_created: 2022-03-18T12:45:09Z
date_published: 2018-12-17T00:00:00Z
date_updated: 2024-10-09T21:02:26Z
day: '17'
department:
- _id: ChLa
doi: 10.1109/cvpr.2018.00956
external_id:
arxiv:
- '1712.08087'
isi:
- '000457843609036'
isi: 1
language:
- iso: eng
main_file_link:
- open_access: '1'
url: ' https://doi.org/10.48550/arXiv.1712.08087'
month: '12'
oa: 1
oa_version: Preprint
page: 9175-9184
publication: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eissn:
- 2575-7075
isbn:
- '9781538664209'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Learning intelligent dialogs for bounding box annotation
type: conference
user_id: c635000d-4b10-11ee-a964-aac5a93f6ac1
year: '2018'
...
---
_id: '18270'
abstract:
- lang: eng
text: The availability of affordable and portable depth sensors has made scanning
objects and people simpler than ever. However, dealing with occlusions and missing
parts is still a significant challenge. The problem of reconstructing a (possibly
non-rigidly moving) 3D object from a single or multiple partial scans has received
increasing attention in recent years. In this work, we propose a novel learning-based
method for the completion of partial shapes. Unlike the majority of existing approaches,
our method focuses on objects that can undergo non-rigid deformations. The core
of our method is a variational autoencoder with graph convolutional operations
that learns a latent space for complete realistic shapes. At inference, we optimize
to find the representation in this latent space that best fits the generated shape
to the known partial input. The completed shape exhibits a realistic appearance
on the unknown part. We show promising results towards the completion of synthetic
and real scans of human body and face meshes exhibiting different styles of articulation
and partiality.
article_number: '8578300'
article_processing_charge: No
arxiv: 1
author:
- first_name: Or
full_name: Litany, Or
last_name: Litany
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Michael
full_name: Bronstein, Michael
last_name: Bronstein
- first_name: Ameesh
full_name: Makadia, Ameesh
last_name: Makadia
citation:
ama: 'Litany O, Bronstein AM, Bronstein M, Makadia A. Deformable shape completion
with graph convolutional autoencoders. In: 2018 IEEE/CVF Conference on Computer
Vision and Pattern Recognition. IEEE; 2018. doi:10.1109/cvpr.2018.00202'
apa: 'Litany, O., Bronstein, A. M., Bronstein, M., & Makadia, A. (2018). Deformable
shape completion with graph convolutional autoencoders. In 2018 IEEE/CVF Conference
on Computer Vision and Pattern Recognition. Salt Lake City, UT, United States:
IEEE. https://doi.org/10.1109/cvpr.2018.00202'
chicago: Litany, Or, Alex M. Bronstein, Michael Bronstein, and Ameesh Makadia. “Deformable
Shape Completion with Graph Convolutional Autoencoders.” In 2018 IEEE/CVF Conference
on Computer Vision and Pattern Recognition. IEEE, 2018. https://doi.org/10.1109/cvpr.2018.00202.
ieee: O. Litany, A. M. Bronstein, M. Bronstein, and A. Makadia, “Deformable shape
completion with graph convolutional autoencoders,” in 2018 IEEE/CVF Conference
on Computer Vision and Pattern Recognition, Salt Lake City, UT, United States,
2018.
ista: Litany O, Bronstein AM, Bronstein M, Makadia A. 2018. Deformable shape completion
with graph convolutional autoencoders. 2018 IEEE/CVF Conference on Computer Vision
and Pattern Recognition. 31st Meeting of the IEEE/CVF Conference on Computer Vision
and Pattern Recognition, 8578300.
mla: Litany, Or, et al. “Deformable Shape Completion with Graph Convolutional Autoencoders.”
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8578300,
IEEE, 2018, doi:10.1109/cvpr.2018.00202.
short: O. Litany, A.M. Bronstein, M. Bronstein, A. Makadia, in:, 2018 IEEE/CVF Conference
on Computer Vision and Pattern Recognition, IEEE, 2018.
conference:
end_date: 2018-06-23
location: Salt Lake City, UT, United States
name: 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
start_date: 2018-06-18
date_created: 2024-10-09T07:41:53Z
date_published: 2018-12-16T00:00:00Z
date_updated: 2024-12-05T14:40:39Z
day: '16'
doi: 10.1109/cvpr.2018.00202
extern: '1'
external_id:
arxiv:
- '1712.00268'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.1712.00268
month: '12'
oa: 1
oa_version: Preprint
publication: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
publication_identifier:
eissn:
- 2575-7075
isbn:
- '9781538664216'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Deformable shape completion with graph convolutional autoencoders
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2018'
...