Metaheuristics Deep Learning for Computer Vision and Image

Dear Colleagues,

Over this last decade, deep learning approaches, including deep convolutional neural networks (CNNs) and vision transformers, have gained popularity for use in computer vision and image processing tasks. Deep CNNs have achieved a remarkable performance in many tasks, such as image classification and object detection, often surpassing human performance. However, current deep learning methods have significant limitations, such as requiring a large number of training images, being challenging to interpret, and necessitating domain expertise to design the network architecture.

Metaheuristic deep learning refers to the methods that explore the use of metaheuristic techniques in developing and implementing deep learning concepts. Indeed, metaheuristics are nature-inspired, population-based algorithms and techniques that offer promising global search capabilities for solving problems without requiring extensive domain expertise. Metaheuristics can solve various problems, such as: 1) automatically designing and optimizing deep neural networks (DNNs), including deep CNNs, RNNs, autoencoders, LSTMs, and GANs, as well as non-NN-based deep models, such as deep support vector machines; 2) compressing deep learning model weights; 3) pruning models; and so on.

This Special Issue aims to investigate the use and development of algorithms involving metaheuristic methods and all types of deep models in applications that solve computer vision and image processing problems.

TOPICS
We would like to invite researchers to submit contributions on the topic from all viewpoints, including theoretical issues, algorithms, systems, and applications. The Special Issue will cover the following possible topics:

• Image processing, e.g., image enhancement, image compression, image restoration, and image reconstruction;
• Edge detection;
• Image segmentation;
• Object detection;
• Image classification;
• Object tracking;
• Medical image analysis;
• Image denoising;
• Video analysis;
• Neural architecture search;
• Optimizing parameters of deep neural networks;
• Optimizing loss functions of deep neural networks;
• Surrogate-assisted evolutionary deep learning methods;
• Multiobjective metaheuristic deep learning methods;
• Computationally efficient metaheuristic deep learning methods;
• Any other emerging topics in metaheuristic deep learning.

Prof. Dr. Amir Nakib
Prof. Dr. Abdelmalik Taleb-Ahmed
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• deep learning
• metaheuristics
• computer vision
• optimization