Computer Vision and Deep Learning: Trends and Applications

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 also from a software development company perspective. The Special Issue will be focused 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 it 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 need to be able to include deep learning solutions into products has led to the emergence of a large demand for “full-stack deep learning”;
• General Adversarial Networks (GAN)—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, more and more 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 that 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 system 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 fewer 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
Guest Editor

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 250 words) can be sent to the Editorial Office for assessment.

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.