Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Taleb, Aiham"'
Autor:
Bergner, Benjamin, Rohrer, Csaba, Taleb, Aiham, Duchrau, Martha, De Leon, Guilherme, Rodrigues, Jonas Almeida, Schwendicke, Falk, Krois, Joachim, Lippert, Christoph
We propose a simple and efficient image classification architecture based on deep multiple instance learning, and apply it to the challenging task of caries detection in dental radiographs. Technically, our approach contributes in two ways: First, it
Externí odkaz:
http://arxiv.org/abs/2112.09694
High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose ContIG, a
Externí odkaz:
http://arxiv.org/abs/2111.13424
Self-supervised learning methods can be used to learn meaningful representations from unlabeled data that can be transferred to supervised downstream tasks to reduce the need for labeled data. In this paper, we propose a 3D self-supervised method tha
Externí odkaz:
http://arxiv.org/abs/2109.14288
Autor:
Taleb, Aiham, Loetzsch, Winfried, Danz, Noel, Severin, Julius, Gaertner, Thomas, Bergner, Benjamin, Lippert, Christoph
Self-supervised learning methods have witnessed a recent surge of interest after proving successful in multiple application fields. In this work, we leverage these techniques, and we propose 3D versions for five different self-supervised methods, in
Externí odkaz:
http://arxiv.org/abs/2006.03829
Self-supervised learning approaches leverage unlabeled samples to acquire generic knowledge about different concepts, hence allowing for annotation-efficient downstream task learning. In this paper, we propose a novel self-supervised method that leve
Externí odkaz:
http://arxiv.org/abs/1912.05396
Autor:
Taleb, Aiham1 (AUTHOR) aiham.taleb@hpi.de, Rohrer, Csaba2 (AUTHOR) csaba.rohrer@charite.de, Bergner, Benjamin1 (AUTHOR) christoph.lippert@hpi.de, De Leon, Guilherme3 (AUTHOR) guilherme@contrasteradiologia.com, Rodrigues, Jonas Almeida4 (AUTHOR) jorodrigues@ufrgs.br, Schwendicke, Falk2 (AUTHOR) falk.schwendicke@charite.de, Lippert, Christoph1,5 (AUTHOR), Krois, Joachim2 (AUTHOR) joachim.krois@charite.de
Publikováno v:
Diagnostics (2075-4418). May2022, Vol. 12 Issue 5, pN.PAG-N.PAG. 15p.
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose ContIG, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c16b60d5721881ef0c45f326c3fb8fb3
https://doi.org/10.1109/cvpr52688.2022.02024
https://doi.org/10.1109/cvpr52688.2022.02024