论文标题
RES-CR-NET，一个残留网络，具有针对显微镜图像的语义分割优化的新型体系结构
Res-CR-Net, a residual network with a novel architecture optimized for the semantic segmentation of microscopy images
论文作者
论文摘要
深神经网络（DNN）已被广泛用于在电子和光学显微镜下执行分割任务。为此目的而开发的大多数DNN是基于编码器型U-NET体系结构的某些变化，并结合了残留块，以提高训练的易于训练和对梯度降解的弹性。在这里，我们介绍了RES-CR-NET，这是一种DNN，其具有残留的块，其中一束可分离的可分离卷积，具有不同的扩张速率或卷积LSTM。每个残留块中使用的过滤器数量以及块的数量是唯一需要修改的超参数，以优化各种不同显微镜图像的网络训练。
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.
