---
OA_place: repository
OA_type: green
_id: '20455'
abstract:
- lang: eng
  text: Despite extensive research since the community learned about adversarial examples
    10 years ago, we still do not know how to train high-accuracy classifiers that
    are guaranteed to be robust to small perturbations of their inputs. Previous works
    often argued that this might be because no classifier exists that is robust and
    accurate at the same time. However, in computer vision this assumption does not
    match reality where humans are usually accurate and robust on most tasks of interest.
    We offer an alternative explanation and show that in certain settings robust generalization
    is only possible with unrealistically large amounts of data. Specifically, we
    find a setting where a robust classifier exists, it is easy to learn an accurate
    classifier, yet it requires an exponential amount of data to learn a robust classifier.
    Based on this theoretical result, we evaluate the influence of the amount of training
    data on datasets such as CIFAR10. Our findings indicate that the the amount of
    training data is the main factor determining the robust performance. Furthermore
    we show that that there are low magnitude directions in the data which are useful
    for non-robust generalization but are not available for robust classifiers. This
    implies that robust classification is a strictly harder tasks than normal classification,
    thereby providing an explanation why robust classification requires more data.
article_processing_charge: No
arxiv: 1
author:
- first_name: Bernd
  full_name: Prach, Bernd
  id: 2D561D42-C427-11E9-89B4-9C1AE6697425
  last_name: Prach
- first_name: Christoph
  full_name: Lampert, Christoph
  id: 40C20FD2-F248-11E8-B48F-1D18A9856A87
  last_name: Lampert
  orcid: 0000-0001-8622-7887
citation:
  ama: 'Prach B, Lampert C. Intriguing properties of robust classification. In: <i>2025
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops</i>.
    IEEE; 2025:660-669. doi:<a href="https://doi.org/10.1109/CVPRW67362.2025.00071">10.1109/CVPRW67362.2025.00071</a>'
  apa: 'Prach, B., &#38; Lampert, C. (2025). Intriguing properties of robust classification.
    In <i>2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops</i>
    (pp. 660–669). Nashville, TN, United States: IEEE. <a href="https://doi.org/10.1109/CVPRW67362.2025.00071">https://doi.org/10.1109/CVPRW67362.2025.00071</a>'
  chicago: Prach, Bernd, and Christoph Lampert. “Intriguing Properties of Robust Classification.”
    In <i>2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops</i>,
    660–69. IEEE, 2025. <a href="https://doi.org/10.1109/CVPRW67362.2025.00071">https://doi.org/10.1109/CVPRW67362.2025.00071</a>.
  ieee: B. Prach and C. Lampert, “Intriguing properties of robust classification,”
    in <i>2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops</i>,
    Nashville, TN, United States, 2025, pp. 660–669.
  ista: 'Prach B, Lampert C. 2025. Intriguing properties of robust classification.
    2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.
    CVPR: Conference on Computer Vision and Pattern Recognition, 660–669.'
  mla: Prach, Bernd, and Christoph Lampert. “Intriguing Properties of Robust Classification.”
    <i>2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops</i>,
    IEEE, 2025, pp. 660–69, doi:<a href="https://doi.org/10.1109/CVPRW67362.2025.00071">10.1109/CVPRW67362.2025.00071</a>.
  short: B. Prach, C. Lampert, in:, 2025 IEEE/CVF Conference on Computer Vision and
    Pattern Recognition Workshops, IEEE, 2025, pp. 660–669.
conference:
  end_date: 2025-06-12
  location: Nashville, TN, United States
  name: 'CVPR: Conference on Computer Vision and Pattern Recognition'
  start_date: 2025-06-11
corr_author: '1'
date_created: 2025-10-12T22:01:26Z
date_published: 2025-06-15T00:00:00Z
date_updated: 2025-10-13T07:18:26Z
day: '15'
department:
- _id: ChLa
doi: 10.1109/CVPRW67362.2025.00071
external_id:
  arxiv:
  - '2412.04245'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.48550/arXiv.2412.04245
month: '06'
oa: 1
oa_version: Preprint
page: 660-669
publication: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
publication_identifier:
  eissn:
  - 2160-7516
  isbn:
  - '9798331599942'
  issn:
  - 2160-7508
publication_status: published
publisher: IEEE
quality_controlled: '1'
related_material:
  record:
  - id: '18874'
    relation: earlier_version
    status: public
scopus_import: '1'
status: public
title: Intriguing properties of robust classification
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
year: '2025'
...
---
_id: '18248'
abstract:
- lang: eng
  text: Learning an object detection or retrieval system requires a large data set
    with manual annotations. Such data are expensive and time-consuming to create
    and therefore difficult to obtain on a large scale. In this work, we propose using
    the natural correlation in narrations and the visual presence of objects in video
    to learn an object detector and retriever without any manual labeling involved.
    We pose the problem as weakly supervised learning with noisy labels, and propose
    a novel object detection and retrieval paradigm under these constraints. We handle
    the background rejection by using contrastive samples and confront the high level
    of label noise with a new clustering score. Our evaluation is based on a set of
    ten objects with manual ground truth annotation in almost 5000 frames extracted
    from instructional videos from the web. We demonstrate superior results compared
    to state-of-the-art weakly- supervised approaches and report a strongly-labeled
    upper bound as well. While the focus of the paper is object detection and retrieval,
    the proposed methodology can be applied to a broader range of noisy weakly-supervised
    problems.
article_number: '9150938'
article_processing_charge: No
author:
- first_name: Elad
  full_name: Amrani, Elad
  last_name: Amrani
- first_name: Rami
  full_name: Ben-Ari, Rami
  last_name: Ben-Ari
- first_name: Inbar
  full_name: Shapira, Inbar
  last_name: Shapira
- first_name: Tal
  full_name: Hakim, Tal
  last_name: Hakim
- first_name: Alexander
  full_name: Bronstein, Alexander
  id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
  last_name: Bronstein
  orcid: 0000-0001-9699-8730
citation:
  ama: 'Amrani E, Ben-Ari R, Shapira I, Hakim T, Bronstein AM. Self-supervised object
    detection and retrieval using unlabeled videos. In: <i>2020 IEEE/CVF Conference
    on Computer Vision and Pattern Recognition Workshops (CVPRW)</i>. IEEE; 2020.
    doi:<a href="https://doi.org/10.1109/cvprw50498.2020.00485">10.1109/cvprw50498.2020.00485</a>'
  apa: 'Amrani, E., Ben-Ari, R., Shapira, I., Hakim, T., &#38; Bronstein, A. M. (2020).
    Self-supervised object detection and retrieval using unlabeled videos. In <i>2020
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</i>.
    Seattle, WA, United States: IEEE. <a href="https://doi.org/10.1109/cvprw50498.2020.00485">https://doi.org/10.1109/cvprw50498.2020.00485</a>'
  chicago: Amrani, Elad, Rami Ben-Ari, Inbar Shapira, Tal Hakim, and Alex M. Bronstein.
    “Self-Supervised Object Detection and Retrieval Using Unlabeled Videos.” In <i>2020
    IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</i>.
    IEEE, 2020. <a href="https://doi.org/10.1109/cvprw50498.2020.00485">https://doi.org/10.1109/cvprw50498.2020.00485</a>.
  ieee: E. Amrani, R. Ben-Ari, I. Shapira, T. Hakim, and A. M. Bronstein, “Self-supervised
    object detection and retrieval using unlabeled videos,” in <i>2020 IEEE/CVF Conference
    on Computer Vision and Pattern Recognition Workshops (CVPRW)</i>, Seattle, WA,
    United States, 2020.
  ista: Amrani E, Ben-Ari R, Shapira I, Hakim T, Bronstein AM. 2020. Self-supervised
    object detection and retrieval using unlabeled videos. 2020 IEEE/CVF Conference
    on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE/CVF Conference
    on Computer Vision and Pattern Recognition Workshops, 9150938.
  mla: Amrani, Elad, et al. “Self-Supervised Object Detection and Retrieval Using
    Unlabeled Videos.” <i>2020 IEEE/CVF Conference on Computer Vision and Pattern
    Recognition Workshops (CVPRW)</i>, 9150938, IEEE, 2020, doi:<a href="https://doi.org/10.1109/cvprw50498.2020.00485">10.1109/cvprw50498.2020.00485</a>.
  short: E. Amrani, R. Ben-Ari, I. Shapira, T. Hakim, A.M. Bronstein, in:, 2020 IEEE/CVF
    Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE,
    2020.
conference:
  end_date: 2020-06-19
  location: Seattle, WA, United States
  name: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
  start_date: 2020-06-14
date_created: 2024-10-08T13:05:08Z
date_published: 2020-07-28T00:00:00Z
date_updated: 2024-12-12T09:59:41Z
day: '28'
doi: 10.1109/cvprw50498.2020.00485
extern: '1'
language:
- iso: eng
month: '07'
oa_version: None
publication: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
  (CVPRW)
publication_identifier:
  eissn:
  - 2160-7516
  isbn:
  - '9781728193618'
publication_status: published
publisher: IEEE
quality_controlled: '1'
scopus_import: '1'
status: public
title: Self-supervised object detection and retrieval using unlabeled videos
type: conference
user_id: 3E5EF7F0-F248-11E8-B48F-1D18A9856A87
year: '2020'
...