Learning Deep Morphological Networks with Neural Architecture Search

TL;DR

This paper introduces a novel method that integrates morphological operators into deep neural networks using meta-learning, significantly enhancing performance on image classification and edge detection tasks.

Contribution

It presents a new approach to incorporate mathematical morphology into DNNs through meta-learning, improving their ability to capture topological features.

Findings

Enhanced accuracy in image classification tasks

Improved edge detection performance

Morphological operators boost DNN feature representation

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.