In recent years, Convolutional Neural Networks (CNNs) have become the state-of-the-art method for biomedical image analysis. However, these networks are usually trained in a supervised manner, requiring large amounts of labelled training data. These labelled data sets are often difficult to acquire in the biomedical domain. In this work, we validate alternative ways to train CNNs with fewer labels for biomedical image segmentation using. We adapt two semi- and self-supervised image classification methods and analyse their performance for semantic segmentation of biomedical microscopy images.
%0 Journal Article
%1 Horlava2020-ze
%A Horlava, Nastassya
%A Mironenko, Alisa
%A Niehaus, Sebastian
%A Wagner, Sebastian
%A Roeder, Ingo
%A Scherf, Nico
%D 2020
%I arXiv
%K
%T A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data
%X In recent years, Convolutional Neural Networks (CNNs) have become the state-of-the-art method for biomedical image analysis. However, these networks are usually trained in a supervised manner, requiring large amounts of labelled training data. These labelled data sets are often difficult to acquire in the biomedical domain. In this work, we validate alternative ways to train CNNs with fewer labels for biomedical image segmentation using. We adapt two semi- and self-supervised image classification methods and analyse their performance for semantic segmentation of biomedical microscopy images.
@article{Horlava2020-ze,
abstract = {In recent years, Convolutional Neural Networks (CNNs) have become the state-of-the-art method for biomedical image analysis. However, these networks are usually trained in a supervised manner, requiring large amounts of labelled training data. These labelled data sets are often difficult to acquire in the biomedical domain. In this work, we validate alternative ways to train CNNs with fewer labels for biomedical image segmentation using. We adapt two semi- and self-supervised image classification methods and analyse their performance for semantic segmentation of biomedical microscopy images.},
added-at = {2024-09-10T11:56:37.000+0200},
author = {Horlava, Nastassya and Mironenko, Alisa and Niehaus, Sebastian and Wagner, Sebastian and Roeder, Ingo and Scherf, Nico},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2394fa51b2426b883dc990ef2a5820a02/scadsfct},
interhash = {1c09ddd89eb1c7afb0a8984670f47842},
intrahash = {394fa51b2426b883dc990ef2a5820a02},
keywords = {},
publisher = {arXiv},
timestamp = {2024-09-10T15:15:57.000+0200},
title = {A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data},
year = 2020
}
