Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
复制标题
DOI：
--
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Sohil Shah;P. Ghosh;L. Davis;T. Goldstein
中科院分区：
文献类型：
--
作者：
Sohil Shah;P. Ghosh;L. Davis;T. Goldstein
许多成像任务需要图像中所有像素的全局信息。传统的自下而上的分类网络通过降低分辨率来全球化信息；特征被汇集并下采样为单个输出。但对于语义分割和对象检测任务，网络必须提供更高分辨率的像素级输出。为了在保持分辨率的同时全球化信息，许多研究人员建议加入复杂的辅助块，但这些是以网络规模和计算成本大幅增加为代价的。本文提出了堆叠式 u-nets（SUNets），它在保持分辨率的同时迭代地组合来自不同分辨率尺度的特征。 SUNet 在更深的网络架构中利用 u-net 的信息全球化能力，能够处理自然图像的复杂性。 SUNet 使用少量参数在语义分割任务上表现得非常好。
Many imaging tasks require global information about all pixels in an image. Conventional bottom-up classification networks globalize information by decreasing resolution; features are pooled and downsampled into a single output. But for semantic segmentation and object detection tasks, a network must provide higher-resolution pixel-level outputs. To globalize information while preserving resolution, many researchers propose the inclusion of sophisticated auxiliary blocks, but these come at the cost of a considerable increase in network size and computational cost. This paper proposes stacked u-nets (SUNets), which iteratively combine features from different resolution scales while maintaining resolution. SUNets leverage the information globalization power of u-nets in a deeper network architectures that is capable of handling the complexity of natural images. SUNets perform extremely well on semantic segmentation tasks using a small number of parameters.