no code implementations • 29 Jul 2022 • Jonas Dippel, Matthias Lenga, Thomas Goerttler, Klaus Obermayer, Johannes Höhne
In this work, we investigate the impact of transfer learning for segmentation problems, being pixel-wise classification problems that can be tackled with encoder-decoder architectures.
no code implementations • MICCAI Workshop COMPAY 2021 • Johannes Höhne, Jacob de Zoete, Arndt A Schmitz, Tricia Bal, Emmanuelle di Tomaso, Matthias Lenga
In this paper, we describe the machine learning problem of identifying different types of tumors based on digital pathology images.
1 code implementation • 9 Apr 2021 • Jonas Dippel, Steffen Vogler, Johannes Höhne
This paper presents Contrastive Reconstruction, ConRec - a self-supervised learning algorithm that obtains image representations by jointly optimizing a contrastive and a self-reconstruction loss.
no code implementations • NeurIPS Workshop Document_Intelligen 2019 • Christian Reisswig, Anoop R Katti, Marco Spinaci, Johannes Höhne
We present an end-to-end trainable approach for optical character recognition (OCR) on printed documents.
no code implementations • 10 Sep 2019 • Christian Reisswig, Anoop R Katti, Marco Spinaci, Johannes Höhne
We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents.
4 code implementations • EMNLP 2018 • Anoop Raveendra Katti, Christian Reisswig, Cordula Guder, Sebastian Brarda, Steffen Bickel, Johannes Höhne, Jean Baptiste Faddoul
We introduce a novel type of text representation that preserves the 2D layout of a document.
no code implementations • 5 Dec 2014 • Daniel Bartz, Johannes Höhne, Klaus-Robert Müller
For the sample mean and the sample covariance as specific instances, we derive conditions under which the optimality of MTS is applicable.