Combined Learning for Similar Tasks with Domain-Switching Networks

Daniel Bug, Dennis Eschweiler, Qianyu Liu, Justus Schock, Leon Weninger, Friedrich Feuerhake, Julia Schüler, Johannes Stegmaier, Dorit Merhof

Abstract

We introduce a domain switch for deep neural networks that enables to re-weight convolutional kernels for an input of a known domain. This technique is designed to address re-occurring tasks across multiple domains that are known at runtime and to incorporate them into a single, domain-spanning network. We evaluate this approach in three distinct tasks, namely combined cell nuclei analysis across different stains and fluorescence images, facial landmark detection in grayscale and thermal infrared images, and the BraTS challenge where we treat different recording institutions as domains. We found that conventional U-nets trained on multiple domains perform similar to domain-specific U-nets. Our method improves the results in facial landmark detection significantly, but no change is measured in the other two experiments compared to multi-domain U-nets.
BibTeX
@inproceedings{bug2019combined,
  author = {Daniel Bug and Dennis Eschweiler and Qianyu Liu and Justus Schock and Leon Weninger and Friedrich Feuerhake and Julia Schüler and Johannes Stegmaier and Dorit Merhof},
  title = {{Combined Learning for Similar Tasks with Domain-Switching Networks}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2019},
  doi = {10.1007/978-3-030-32254-0\_63},
}

Loading related content...

Figure