Deep Learning in Image Processing and Scientific Computing

Dear Colleagues,

Recent advancements in the application of deep neural networks in large-scale visual recognition challenges, as well as in other domains, has led to an explosion of research in the field of deep learning. Deep-learning-related research is revolutionizing various industries and domains. The success of deep learning models can be attributed to several factors, including the availability of large-scale datasets, advances in computing power, and innovations in model architectures. Various deep learning architectures have been proposed over the last decade to tackle different types of tasks, such as convolutional neural networks, recurrent neural networks, graph neural networks, and transformers. While the empirical success of these architectures is evident, researchers are also endeavoring to understand the theoretical principles underlying these deep learning successes. Some ongoing research areas include the theoretical understanding of generalization, interpretable deep learning, robustness and adversarial attacks, training efficiency and transfer learning, etc.

The primary objective of this Special Issue is to address cutting-edge advancements in the rapidly evolving field of deep learning. In particular, we invite authors to submit papers that showcase the robustness and generalizability of their models or methodologies. By gathering such diverse and innovative works, we aim to present a compelling collection that captures the forefront of deep learning research. We welcome both original research contributions and review articles.

Potential topics include, but are not limited to, the following:

• General deep learning: supervised, semi-, and self-supervised learning, meta learning, active learning, transfer learning, few-shot learning, continual learning, efficient deep learning, etc.
• Deep learning architectures: convolutional neural networks, recurrent neural networks, graph neural networks, and Transformers, etc.
• Trustworthy deep learning: generalization, interpretability, accountability, fairness, privacy, robustness and adversarial attacks, etc.
• Image and video understanding: image retrieval and classification, object detection and localization, action recognition, etc.
• Image and video synthesis: manipulation, generation, rendering, restoration, enhancement, and visualization
• Deep learning in imaging applications: medical, biological, electronic imaging, remote sensing, etc.
• Deep learning for scientific computing: climate, health, life sciences, physics, social sciences, etc.

Dr. Xuqing Wu
Dr. Siyu Huang
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.

• machine learning
• deep learning
• neural networks
• computer vision
• image processing
• AI-generated content
• AI for science