Advances, Challenges, and Applications of Deep Learning Models in Computer Vision and Image Processing and Analysis

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".

Deadline for manuscript submissions: 31 August 2025 | Viewed by 401

Special Issue Editors


E-Mail Website
Guest Editor
Faculty of Engineering, Autonomous University of San Luis Potosi, San Luis Potosí 78290, Mexico
Interests: signal, image, and video processing; computer vision; heterogeneous computing; machine learning; deep learning; embedded systems design; electronic circuit design

E-Mail Website
Guest Editor
Faculty of Engineering, Autonomous University of San Luis Potosi, San Luis Potosí 78290, Mexico
Interests: evolutionary computation applied to computer vision; machine learning; deep learning; image and signal processing; remote sensing

Special Issue Information

Dear Colleagues,

Deep learning (DL) models have gained crucial importance in the field of machine learning, especially in the research areas of computer vision and image processing and analysis. The widespread use of DL models is attributed to a strong mathematical foundation, innovation in theoretical and technological research, and broad applications in diverse domains such as healthcare and medicine, industry and commerce, robotics and autonomous vehicles, cybersecurity and surveillance, agriculture and forestry, and remote sensing and geospatial analysis, to name a few.

Despite numerous obstacles facing DL models, such as the need for massive amounts of labeled data, high training costs, scale, translation and rotation invariance in object recognition, adversarial attacks, and their increasing mathematical complexity, recent advances continue to push DL models forward, addressing one or more of the aforementioned challenges. These advances include more robust convolutional neural networks, recurrent neural networks, generative adversarial networks, capsule neural networks, novel deep transfer learning techniques, vision transformers, and hybrid DL architectures, among others.

This Special Issue calls for original research articles and reviews that contribute to the latest advances and applications of DL models in computer vision and image processing and analysis, particularly those focused on real-world problems, as well as articles that explore the challenges of DL models along with trends and ways to address them.

Dr. Carlos Soubervielle-Montalvo
Dr. Cesar Puente
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.

Keywords

  • deep learning
  • computer vision
  • image processing
  • image analysis
  • convolutional neural networks
  • recurrent neural networks
  • generative adversarial networks
  • capsule neural networks
  • deep transfer learning
  • vision transformers
  • hybrid deep learning architecture
  • image classification
  • image segmentation
  • object recognition
  • video tracking
  • adversarial attacks
  • healthcare and medicine
  • autonomous vehicles
  • cybersecurity
  • surveillance
  • artistic-style classification
  • agriculture and forestry
  • remote sensing and geospatial analysis

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

23 pages, 2486 KiB  
Article
Learning High-Order Features for Fine-Grained Visual Categorization with Causal Inference
by Yuhang Zhang, Yuan Wan, Jiahui Hao, Zaili Yang and Huanhuan Li
Mathematics 2025, 13(8), 1340; https://doi.org/10.3390/math13081340 - 19 Apr 2025
Viewed by 145
Abstract
Recently, causal models have gained significant attention in natural language processing (NLP) and computer vision (CV) due to their capability of capturing features with causal relationships. This study addresses Fine-Grained Visual Categorization (FGVC) by incorporating high-order feature fusions to improve the representation of [...] Read more.
Recently, causal models have gained significant attention in natural language processing (NLP) and computer vision (CV) due to their capability of capturing features with causal relationships. This study addresses Fine-Grained Visual Categorization (FGVC) by incorporating high-order feature fusions to improve the representation of feature interactions while mitigating the influence of confounding factors through causal inference. A novel high-order feature learning framework with causal inference is developed to enhance FGVC. A causal graph tailored to FGVC is constructed, and the causal assumptions of baseline models are analyzed to identify confounding factors. A reconstructed causal structure establishes meaningful interactions between individual images and image pairs. Causal interventions are applied by severing specific causal links, effectively reducing confounding effects and enhancing model robustness. The framework combines high-order feature fusion with interventional fine-grained learning by performing causal interventions on both classifiers and categories. The experimental results demonstrate that the proposed method achieves accuracies of 90.7% on CUB-200, 92.0% on FGVC-Aircraft, and 94.8% on Stanford Cars, highlighting its effectiveness and robustness across these widely used fine-grained recognition datasets. Comprehensive evaluations of these three widely used fine-grained recognition datasets demonstrate the proposed framework’s effectiveness and robustness. Full article
Show Figures

Figure 1

Back to TopTop