arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.08063cs.LGcs.CVeess.IV
收藏

构件树损失函数的定义与优化

Component Tree Loss Function: Definition and Optimization

LIGM(加斯帕尔·蒙日信息学实验室);Univ Gustave Eiffel(古斯塔夫·埃菲尔大学);CNRS(法国国家科学研究中心);ESIEE Paris(巴黎高等电子工程师学院)

Benjamin Perret, Jean Cousty

摘要:

在这篇文章中,我们提出了一种方法来设计损失函数的基础上的组件树,可以优化的梯度下降算法,因此,可与最近的机器学习方法,如神经网络。我们展示了如何与这种分层图像表示的节点相关联的海拔高度可以区分相对于图像像素值。该特征用于设计通用的损失函数,其可以基于诸如消光值的各种属性来选择或丢弃图像最大值。仿真和实际图像滤波的可能性,所提出的方法被证明。

英文摘要:

In this article, we propose a method to design loss functions based on component trees which can be optimized by gradient descent algorithms and which are therefore usable in conjunction with recent machine learning approaches such as neural networks. We show how the altitudes associated to the nodes of such hierarchical image representations can be differentiated with respect to the image pixel values. This feature is used to design a generic loss function that can select or discard image maxima based on various attributes such as extinction values. The possibilities of the proposed method are demonstrated on simulated and real image filtering.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑