Dense Transformer Networks for Brain Electron Microscopy Image Segmentation-猫眼课题宝

DOI：

10.24963/ijcai.2019/401

发表时间：

2019-08

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Jun Li;Yongjun Chen;Lei Cai;I. Davidson;Shuiwang Ji

当前的深度学习方法的密集预测方法的关键思想是将模型应用于以每个像素为中心的常规贴片上，以对像素进行预测。这些方法是有限的，因为这些方法是由网络体系结构确定而不是从数据中学到的。在这项工作中，我们提出了密集的变压器网络，该网络可以从数据中学习形状和尺寸。密集的变压器网络采用编码器架构，将一对密集的变压器模块插入到每个编码器和解码器路径中。这项工作的新颖性是，我们提供了技术解决方案，以学习数据的形状和大小，并有效地恢复了密集预测所需的空间对应关系。所提出的密集变压器模块是可区分的，因此可以训练整个网络。我们将提出的网络应用于生物图像分割任务上，并且与基线方法相比，表现出卓越的性能。

The key idea of current deep learning methods for dense prediction is to apply a model on a regular patch centered on each pixel to make pixel-wise predictions. These methods are limited in the sense that the patches are determined by network architecture instead of learned from data. In this work, we propose the dense transformer networks, which can learn the shapes and sizes of patches from data. The dense transformer networks employ an encoder-decoder architecture, and a pair of dense transformer modules are inserted into each of the encoder and decoder paths. The novelty of this work is that we provide technical solutions for learning the shapes and sizes of patches from data and efficiently restoring the spatial correspondence required for dense prediction. The proposed dense transformer modules are differentiable, thus the entire network can be trained. We apply the proposed networks on biological image segmentation tasks and show superior performance is achieved in comparison to baseline methods.

Dense Transformer Networks for Brain Electron Microscopy Image Segmentation

文献摘要

相似文献