Instance Segmentation as Image Segmentation Annotation
Instance Segmentation as Image Segmentation Annotation
复制标题
DOI：
10.1109/ivs.2019.8814026
复制
发表时间：
2019-02
期刊：
影响因子：
--
通讯作者：
Thomio Watanabe;D. Wolf
中科院分区：
文献类型：
--
作者：
Thomio Watanabe;D. Wolf
实例分割问题旨在精确地检测和描绘图像中的对象。目前的大多数解决方案都依赖于深度卷积神经网络，但尽管如此，提出的解决方案仍然非常多样化。一些解决方案将问题作为网络问题来处理，其中它们使用多个网络或专用于单个网络来解决多个任务。另一种方法试图将问题作为注释问题来解决，其中实例信息以数学表示形式编码。本文提出了一种基于DCME技术的解决方案，利用单个分割网络解决实例分割问题。与其他网络解码器不同的是，分段网络解码器不是专门用于多任务网络的。相反，网络编码器被重新用于对图像对象进行分类，从而降低了解决方案的计算成本。
The instance segmentation problem intends to precisely detect and delineate objects in images. Most of the current solutions rely on deep convolutional neural networks but despite this fact proposed solutions are very diverse. Some solutions approach the problem as a network problem, where they use several networks or specialize a single network to solve several tasks. A different approach tries to solve the problem as an annotation problem, where the instance information is encoded in a mathematical representation. This work proposes a solution based in the DCME technique to solve the instance segmentation with a single segmentation network. Different from others, the segmentation network decoder is not specialized in a multi-task network. Instead, the network encoder is repurposed to classify image objects, reducing the computational cost of the solution.