arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.07714cs.CVcs.AIcs.LG
收藏

使用神经结构搜索学习深度形态网络

Learning Deep Morphological Networks with Neural Architecture Search

ENSTA Paris, Institut Polytechnique de Paris(巴黎高等先进技术学院,巴黎理工学院);Safrantech, Safran Group(赛峰技术公司,赛峰集团);Mines ParisTech, PSL Research University(巴黎高等矿业学院,巴黎文理研究大学);National University of Singapore(新加坡国立大学)

Yufei Hu, Nacim Belkhir, Jesus Angulo, Angela Yao, Gianni Franchi

摘要:

深度神经网络(DNN)是通过顺序执行线性和非线性过程生成的。使用线性和非线性过程的组合对于生成足够深的特征空间至关重要。大多数非线性算子是激活函数或池函数的导数。数学形态学是为各种图像处理问题提供非线性算子的数学分支。在本文中,我们研究了在端到端深度学习框架中集成这些操作的实用性。DNN旨在为特定作业获取真实的表示。形态学算子给出拓扑描述符,其传达关于图像中描绘的对象的形状的显著信息。我们提出了一种基于元学习的方法,将形态算子纳入DNN。学习的架构展示了我们的新形态操作如何显着提高DNN在各种任务上的性能,包括图片分类和边缘检测。

英文摘要:

Deep Neural Networks (DNNs) are generated by sequentially performing linear and non-linear processes. Using a combination of linear and non-linear procedures is critical for generating a sufficiently deep feature space. The majority of non-linear operators are derivations of activation functions or pooling functions. Mathematical morphology is a branch of mathematics that provides non-linear operators for a variety of image processing problems. We investigate the utility of integrating these operations in an end-to-end deep learning framework in this paper. DNNs are designed to acquire a realistic representation for a particular job. Morphological operators give topological descriptors that convey salient information about the shapes of objects depicted in images. We propose a method based on meta-learning to incorporate morphological operators into DNNs. The learned architecture demonstrates how our novel morphological operations significantly increase DNN performance on various tasks, including picture classification and edge detection.

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。

↑