LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Zurück zur letzten Suche Suchhistorie
Erweiterte Suche

Ihre letzten Suchen

  1. AU="Dröge, Hannah"
  2. AU=Heinold B
  3. AU="Essaidi, Zakaria"
  4. AU="Polifka, Richard"
  5. AU=Epstein Marina
  6. AU="Meier, Nicole"
  7. AU="Hamill, Vaughn"
  8. AU="Fadwa M. AlKhulaifi"
  9. AU="Ghazal, Mohammed"
  10. AU="Kang, Ligai"
  11. AU=Hofmann Matthias
  12. AU="Nagehan Emiralioglu"
  13. AU="Zhao, Wen-yu"
  14. AU="Canel, Clémence"
  15. AU="Cubas-Atienzar, Ana I"
  16. AU=Helmke Steve
  17. AU=de la Fuente Jose AU=de la Fuente Jose
  18. AU="Shamsudduha, M"
  19. AU=Lee Jessica J. Y.
  20. AU=Wen Xue
  21. AU="Frasca, Graziella"
  22. AU="Kim, Christopher"
  23. AU="Ammerlaan, Carola M E"
  24. AU="Argañaraz, Gustavo A"
  25. AU="Del Fernandes, Rosephine"
  26. AU="Lei, Wei-Yi"
  27. AU="Sandile Cele"
  28. AU=Benzinger Tammie L S
  29. AU="Fallah, Nader Nader"

Suchergebnis

Treffer 1 - 3 von insgesamt 3

Suchoptionen

  1. Buch ; Online: Kissing to Find a Match

    Dröge, Hannah / Lähner, Zorah / Bahat, Yuval / Martorell, Onofre / Heide, Felix / Möller, Michael

    Efficient Low-Rank Permutation Representation

    2023  

    Abstract: Permutation matrices play a key role in matching and assignment problems across the fields, especially in computer vision and robotics. However, memory for explicitly representing permutation matrices grows quadratically with the size of the problem, ... ...

    Abstract Permutation matrices play a key role in matching and assignment problems across the fields, especially in computer vision and robotics. However, memory for explicitly representing permutation matrices grows quadratically with the size of the problem, prohibiting large problem instances. In this work, we propose to tackle the curse of dimensionality of large permutation matrices by approximating them using low-rank matrix factorization, followed by a nonlinearity. To this end, we rely on the Kissing number theory to infer the minimal rank required for representing a permutation matrix of a given size, which is significantly smaller than the problem size. This leads to a drastic reduction in computation and memory costs, e.g., up to $3$ orders of magnitude less memory for a problem of size $n=20000$, represented using $8.4\times10^5$ elements in two small matrices instead of using a single huge matrix with $4\times 10^8$ elements. The proposed representation allows for accurate representations of large permutation matrices, which in turn enables handling large problems that would have been infeasible otherwise. We demonstrate the applicability and merits of the proposed approach through a series of experiments on a range of problems that involve predicting permutation matrices, from linear and quadratic assignment to shape matching problems.

    Comment: 13 pages, 6 figures
    Schlagwörter Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition
    Thema/Rubrik (Code) 511
    Erscheinungsdatum 2023-08-25
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  2. Artikel ; Online: Mitral Valve Segmentation Using Robust Nonnegative Matrix Factorization.

    Dröge, Hannah / Yuan, Baichuan / Llerena, Rafael / Yen, Jesse T / Moeller, Michael / Bertozzi, Andrea L

    Journal of imaging

    2021  Band 7, Heft 10

    Abstract: Analyzing and understanding the movement of the mitral valve is of vital importance in cardiology, as the treatment and prevention of several serious heart diseases depend on it. Unfortunately, large amounts of noise as well as a highly varying image ... ...

    Abstract Analyzing and understanding the movement of the mitral valve is of vital importance in cardiology, as the treatment and prevention of several serious heart diseases depend on it. Unfortunately, large amounts of noise as well as a highly varying image quality make the automatic tracking and segmentation of the mitral valve in two-dimensional echocardiographic videos challenging. In this paper, we present a fully automatic and unsupervised method for segmentation of the mitral valve in two-dimensional echocardiographic videos, independently of the echocardiographic view. We propose a bias-free variant of the robust non-negative matrix factorization (RNMF) along with a window-based localization approach, that is able to identify the mitral valve in several challenging situations. We improve the average f1-score on our dataset of 10 echocardiographic videos by 0.18 to a f1-score of 0.56.
    Sprache Englisch
    Erscheinungsdatum 2021-10-16
    Erscheinungsland Switzerland
    Dokumenttyp Journal Article
    ZDB-ID 2824270-1
    ISSN 2313-433X ; 2313-433X
    ISSN (online) 2313-433X
    ISSN 2313-433X
    DOI 10.3390/jimaging7100213
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

  3. Buch ; Online: Inverting Gradients -- How easy is it to break privacy in federated learning?

    Geiping, Jonas / Bauermeister, Hartmut / Dröge, Hannah / Moeller, Michael

    2020  

    Abstract: The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates (gradients) based on local data. This protocol has been designed not only ... ...

    Abstract The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates (gradients) based on local data. This protocol has been designed not only to train neural networks data-efficiently, but also to provide privacy benefits for users, as their input data remains on device and only parameter gradients are shared. But how secure is sharing parameter gradients? Previous attacks have provided a false sense of security, by succeeding only in contrived settings - even for a single image. However, by exploiting a magnitude-invariant loss along with optimization strategies based on adversarial attacks, we show that is is actually possible to faithfully reconstruct images at high resolution from the knowledge of their parameter gradients, and demonstrate that such a break of privacy is possible even for trained deep networks. We analyze the effects of architecture as well as parameters on the difficulty of reconstructing an input image and prove that any input to a fully connected layer can be reconstructed analytically independent of the remaining architecture. Finally we discuss settings encountered in practice and show that even averaging gradients over several iterations or several images does not protect the user's privacy in federated learning applications in computer vision.

    Comment: 23 pages, 20 figures. The first three authors contributed equally
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Cryptography and Security ; Computer Science - Machine Learning
    Thema/Rubrik (Code) 004
    Erscheinungsdatum 2020-03-31
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang