论文标题
重新考虑无监督的神经超像素细分
Rethinking Unsupervised Neural Superpixel Segmentation
论文作者
论文摘要
最近，已经研究了通过CNN进行无监督学习对超像素分割的概念。从本质上讲，这种方法通过单个图像上使用的卷积神经网络（CNN）生成超像素，并且对此类CNN进行了培训，而无需任何标签或更多信息。因此，这种方法依赖于先验的掺入，通常是通过设计一个目标函数，该目标函数可以指导解决方案实现有意义的超像素分割。在本文中，我们提出了三个关键要素，以提高此类网络的功效：（i）与输入图像相比，\ emph {soft} superpicles的图像的相似性，（ii）对象边缘和边界和边界和（iii）基于Atrous的架构的增强和考虑，该体系结构允许较宽的群体构建跨越型号的互联网络。通过尝试BSDS500数据集，我们在定性和定量上找到了提案的重要性的证据。
Recently, the concept of unsupervised learning for superpixel segmentation via CNNs has been studied. Essentially, such methods generate superpixels by convolutional neural network (CNN) employed on a single image, and such CNNs are trained without any labels or further information. Thus, such approach relies on the incorporation of priors, typically by designing an objective function that guides the solution towards a meaningful superpixel segmentation. In this paper we propose three key elements to improve the efficacy of such networks: (i) the similarity of the \emph{soft} superpixelated image compared to the input image, (ii) the enhancement and consideration of object edges and boundaries and (iii) a modified architecture based on atrous convolution, which allow for a wider field of view, functioning as a multi-scale component in our network. By experimenting with the BSDS500 dataset, we find evidence to the significance of our proposal, both qualitatively and quantitatively.
