Learning Deep Morphological Networks with Neural Architecture Search
Abstract
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.
Cite
@article{arxiv.2106.07714,
title = {Learning Deep Morphological Networks with Neural Architecture Search},
author = {Yufei Hu and Nacim Belkhir and Jesus Angulo and Angela Yao and Gianni Franchi},
journal= {arXiv preprint arXiv:2106.07714},
year = {2022}
}
Comments
18 pages