Learning Deep Morphological Networks with Neural Architecture Search
This work addresses the need for more effective non-linear operators in deep learning for image processing, offering a novel integration method that could benefit computer vision applications.
The paper tackled the problem of enhancing deep neural networks by integrating morphological operators for better shape and topological feature extraction, resulting in significant performance improvements on tasks like image classification and edge detection.
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.