Abstract
In this paper, we aim at solving pixel-wise binary problems, including salient object segmentation, skeleton extraction, and edge detection, by introducing a unified architecture. Previous works have proposed tailored methods for solving each of the three tasks independently. Here, we show that these tasks share some similarities that can be exploited for developing a unified framework. In particular, we introduce a horizontal cascade, each component of which is densely connected to the outputs of previous component. Stringing these components together allows us to effectively exploit features across different levels hierarchically to effectively address the multiple pixel-wise binary regression tasks. To assess the performance of our proposed network on these tasks, we carry out exhaustive evaluations on multiple representative datasets. Although these tasks are inherently very different, we show that our unified approach performs very well on all of them and works far better than current single-purpose state-of-the-art methods. All the code in this paper will be publicly available.
Abstract (translated)
本文旨在通过引入一个统一的体系结构来解决像素级的二进制问题，包括突出的对象分割、骨架提取和边缘检测。以前的工作提出了独立解决这三个任务的量身定制方法。在这里，我们展示了这些任务具有一些相似性，可以利用这些相似性来开发一个统一的框架。特别地，我们引入一个水平级联，其中的每个组件都与前一个组件的输出紧密相连。将这些组件串在一起可以有效地利用不同层次的特性，从而有效地处理多像素的二进制回归任务。为了评估我们提出的网络在这些任务上的性能，我们对多个具有代表性的数据集进行了详尽的评估。尽管这些任务本质上是非常不同的，但我们表明，我们的统一方法在所有这些任务上都表现得非常好，并且比当前的单用途最先进的方法效果要好得多。本文中的所有代码都是公开的。
URL
https://arxiv.org/abs/1803.09860
