Res-CR-Net, a residual network with a novel architecture optimized for the semantic segmentation of microscopy images
Deep Neural Networks (DNN) have been widely used to carry out segmentation tasks in both electron and light microscopy. Most DNNs developed for this purpose are based on some variation of the encoder-decoder type U-Net architecture, in combination with residual blocks to increase ease of training an...
Saved in:
Main Authors | , , , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
14.04.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Deep Neural Networks (DNN) have been widely used to carry out segmentation
tasks in both electron and light microscopy. Most DNNs developed for this
purpose are based on some variation of the encoder-decoder type U-Net
architecture, in combination with residual blocks to increase ease of training
and resilience to gradient degradation. Here we introduce Res-CR-Net, a type of
DNN that features residual blocks with either a bundle of separable atrous
convolutions with different dilation rates or a convolutional LSTM. The number
of filters used in each residual block and the number of blocks are the only
hyperparameters that need to be modified in order to optimize the network
training for a variety of different microscopy images. |
---|---|
DOI: | 10.48550/arxiv.2004.08246 |