Computer Vision and Deep Learning: Trends and Applications (2nd Edition)

Dear Colleagues,

The aim of this Special Issue is to discuss the latest innovations in deep learning technologies applied to computer vision and image processing contexts from a software development company perspective. The Special Issue will focus on:

• No-Code Deep Learning—a way of programming DL applications without having to go through the long and arduous processes of pre-processing, modeling, designing algorithms, collecting new data, retraining, deployment, and more;
• TinyDL—IoT-driven; while large-scale machine learning applications exist, their usability is fairly limited. Smaller-scale applications are often necessary. It can take time for a web request to send data to a large server for them to be processed by a machine learning algorithm and then sent back;
• Full-Stack Deep Learning—a form of wide spreading of deep learning frameworks; the business needs to be able to include deep learning solutions into products, which has led to the emergence of a large demand for “full-stack deep learning”;
• General Adversarial Networks (GANs)—a way of producing stronger solutions for implementations such as differentiating between different kinds of images. Generative neural networks produce samples that must be checked by discriminative networks which toss out unwanted generated content;
• Unsupervised and Self-Supervised DL—as automation improves, increased data science solutions are needed without human intervention. We already know from previous techniques that machines cannot learn in a vacuum. They must be able to take new information and analyze those data for the solution that they provide. However, this typically requires human data scientists to feed that information into the system;
• Reinforcement Learning—where the machine learning system learns from direct experiences with its environment. The environment can use reward/punishment systems to assign value to the observations that the ML system sees;
• Few-Shot, One-Shot, and Zero-Shot Learning—few-shot learning focuses on limited data. While this has limitations, it does have various applications in fields such as image classification, facial recognition, and text classification. Likewise, one-shot learning uses even less data. Zero-shot learning is an initially confusing prospect. How can machine learning algorithms function without initial data? Zero-shot ML systems observe a subject and use information about that object to predict what classification they may fall into. This is possible for humans.

Dr. Pier Luigi Mazzeo
Dr. Alessandro Bruno
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. Journal of Imaging is an international peer-reviewed open access monthly 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 1800 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
• machine learning
• reinforcement learning
• unsupervised and self-supervised learning
• general adversarial networks (GANs)
• no-code machine learning
• full-stack deep learning
• few-shot, one-shot, and zero-shot learning
• tiny machine learning

• Computer Vision and Deep Learning: Trends and Applications in Journal of Imaging (14 articles)