---
_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: <i>2019 IEEE/CVF
    Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE; 2020.
    doi:<a href="https://doi.org/10.1109/cvpr.2019.00534">10.1109/cvpr.2019.00534</a>'
  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 <i>2019 IEEE/CVF Conference on Computer Vision
    and Pattern Recognition (CVPR)</i>. Long Beach, CA, United States: IEEE. <a href="https://doi.org/10.1109/cvpr.2019.00534">https://doi.org/10.1109/cvpr.2019.00534</a>'
  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 <i>2019
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE,
    2020. <a href="https://doi.org/10.1109/cvpr.2019.00534">https://doi.org/10.1109/cvpr.2019.00534</a>.'
  ieee: 'L. Karlinsky <i>et al.</i>, “Repmet: Representative-based metric learning
    for classification and few-shot object detection,” in <i>2019 IEEE/CVF Conference
    on Computer Vision and Pattern Recognition (CVPR)</i>, 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.” <i>2019 IEEE/CVF Conference on
    Computer Vision and Pattern Recognition (CVPR)</i>, 8953439, IEEE, 2020, doi:<a
    href="https://doi.org/10.1109/cvpr.2019.00534">10.1109/cvpr.2019.00534</a>.'
  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: <i>2019 IEEE/CVF Conference on Computer
    Vision and Pattern Recognition (CVPR)</i>. IEEE; 2020. doi:<a href="https://doi.org/10.1109/cvpr.2019.00671">10.1109/cvpr.2019.00671</a>'
  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 <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition
    (CVPR)</i>. Long Beach, CA, United States: IEEE. <a href="https://doi.org/10.1109/cvpr.2019.00671">https://doi.org/10.1109/cvpr.2019.00671</a>'
  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 <i>2019 IEEE/CVF Conference on
    Computer Vision and Pattern Recognition (CVPR)</i>. IEEE, 2020. <a href="https://doi.org/10.1109/cvpr.2019.00671">https://doi.org/10.1109/cvpr.2019.00671</a>.'
  ieee: 'A. Alfassy <i>et al.</i>, “Laso: Label-set operations networks for multi-label
    few-shot learning,” in <i>2019 IEEE/CVF Conference on Computer Vision and Pattern
    Recognition (CVPR)</i>, 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.” <i>2019 IEEE/CVF Conference on Computer Vision and Pattern
    Recognition (CVPR)</i>, 8954088, IEEE, 2020, doi:<a href="https://doi.org/10.1109/cvpr.2019.00671">10.1109/cvpr.2019.00671</a>.'
  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: <i>2019 IEEE/CVF Conference on Computer Vision
    and Pattern Recognition (CVPR)</i>. IEEE; 2020. doi:<a href="https://doi.org/10.1109/cvpr.2019.00450">10.1109/cvpr.2019.00450</a>'
  apa: 'Halimi, O., Litany, O., Rodola, E. R., Bronstein, A. M., &#38; Kimmel, R.
    (2020). Unsupervised learning of dense shape correspondence. In <i>2019 IEEE/CVF
    Conference on Computer Vision and Pattern Recognition (CVPR)</i>. Long Beach,
    CA, United States: IEEE. <a href="https://doi.org/10.1109/cvpr.2019.00450">https://doi.org/10.1109/cvpr.2019.00450</a>'
  chicago: Halimi, Oshri, Or Litany, Emanuele Rodola Rodola, Alex M. Bronstein, and
    Ron Kimmel. “Unsupervised Learning of Dense Shape Correspondence.” In <i>2019
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>. IEEE,
    2020. <a href="https://doi.org/10.1109/cvpr.2019.00450">https://doi.org/10.1109/cvpr.2019.00450</a>.
  ieee: O. Halimi, O. Litany, E. R. Rodola, A. M. Bronstein, and R. Kimmel, “Unsupervised
    learning of dense shape correspondence,” in <i>2019 IEEE/CVF Conference on Computer
    Vision and Pattern Recognition (CVPR)</i>, 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.”
    <i>2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</i>,
    8953366, IEEE, 2020, doi:<a href="https://doi.org/10.1109/cvpr.2019.00450">10.1109/cvpr.2019.00450</a>.
  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'
...