Automatic image segmentation technology is critical to the visual analysis. The autoencoder architecture has satisfying performance in various image segmentation tasks. However, autoencoders based on convolutional neural networks (CNN) seem to encounter a bottleneck in improving the accuracy of semantic segmentation. Increasing the inter-class distance between foreground and background is an inherent characteristic of the segmentation network. However, segmentation networks pay too much attention to the main visual difference between foreground and background, and ignores the detailed edge information, which leads to a reduction in the accuracy of edge segmentation. In this paper, we propose a light-weight end-to-end segmentation framework based on multi-task learning, termed Edge Attention autoencoder Network (EAA-Net), to improve edge segmentation ability. Our approach not only utilizes the segmentation network to obtain inter-class features, but also applies the reconstruction network to extract intra-class features among the foregrounds. We further design a intra-class and inter-class features fusion module -- I2 fusion module. The I2 fusion module is used to merge intra-class and inter-class features, and use a soft attention mechanism to remove invalid background information. Experimental results show that our method performs well in medical image segmentation tasks. EAA-Net is easy to implement and has small calculation cost.
翻译:自动图像分割技术对视觉分析至关重要。 自动编码器结构满足了各种图像分割任务中的性能。 但是, 基于 convolutional 神经网络(CNN) 的自动编码器在提高语义分割准确性方面似乎遇到了瓶颈。 增加前景和背景之间的分类间距离是分割网络的固有特征。 但是, 分割网络过于关注前景和背景之间的主要视觉差异, 忽略了详细的边缘信息, 从而降低了边缘分割的准确性。 在本文中, 我们建议基于多任务学习的轻量端对端分割框架, 称为 Edge Descent Autencoder 网络( EAA- Net ), 以提高边缘分割能力。 我们的方法不仅利用分层网络获得分层特征, 而且还应用重建网络在前景中提取类内部特征。 我们进一步设计一个内部和分级特征融合模块 -- I2 融合模块。 I2 软化终端对网络分割模块的轻度端对端对终端分割框架分割框架分割框架分割框架框架框架框架框架框架框架框架框架, 将用来消除内部分析结果, 并用常规分析分析分析分析分析分析结果, 以显示内部和内部分析分析分析结果, 以分析分析结果, 以分析分析分析分析分析结果, 以分析分析分析结果, 以分析分析分析分析结果, 以分析结果分析结果分析结果分析结果,, 以分析结果 以分析分析结果分析结果 以分析结果 以分析结果 分析结果 。