NeurIPS 22 Workshop - Medical Imaging meets NeurIPS · 2022
Does Medical Imaging learn different Convolution Filters?
Why this publication matters
Medical images look very different from everyday photographs, so it is natural to expect their AI models to learn entirely different basic patterns. This study finds that some apparent differences instead come from network design. That strengthens the case for studying when broadly available pretraining can help specialized imaging tasks.
Abstract
Recent work has investigated the distributions of learned convolution filters through a large-scale study containing hundreds of heterogeneous image models. Surprisingly, on average, the distributions only show minor drifts in comparisons of various studied dimensions including the learned task, image domain, or dataset. However, among the studied image domains, medical imaging models appeared to show significant outliers through “spikey” distributions, and, therefore, learn clusters of highly specific filters different from other domains. Following this observation, we study the collected medical imaging models in more detail. We show that instead of fundamental differences, the outliers are due to specific processing in some architectures. Quite the contrary, for standardized architectures, we find that models trained on medical data do not significantly differ in their filter distributions from similar architectures trained on data from other domains. Our conclusions reinforce previous hypotheses stating that pre-training of imaging models can be done with any kind of diverse image data.
Figures
Cite this paper
@inproceedings{gavrikov2022doesmedicalimaging20,
title = {{Does Medical Imaging learn different Convolution Filters?}},
author = {Paul Gavrikov and Janis Keuper},
booktitle = {NeurIPS 22 Workshop - Medical Imaging meets NeurIPS},
year = {2022},
url = {https://arxiv.org/abs/2210.13799}
}
Figures and abstract are reproduced from the linked research sources. Credit remains with the authors and publishers.