Collection

Resource Efficient Deep Learning for Computer Vision Applications

Submission status
Open
Open for submission from
13 December 2023
Submission deadline
30 October 2024
Despite the success of deep learning models in many areas, they have been emerging at the cost of increasingly large scale of models, which require powerful computing and data resources. However, as a common situation in practical computer vision applications, especially on the edge side such as mobile applications, resource limitations are something that must be considered, such as limited computing power, high real-time requirement, and insufficient data. Thus, resource-constrained deep learning theories, methods and applications should receive enough attention. There exist several different directions towards making deep learning efficient for computer vision, thereby leading to a reduction in the required data set size, computational memory or the associated training and inference time. Most research that exists focuses on making deep learning methods efficient, however, the resource associated with real-world mobile devices can vary drastically, and a method termed efficient for a certain choice of resource budgets might be completely inefficient for a different one. This special issue focuses on budget-aware model training and inference, thereby maximally utilizing the available resources of data and computing.

Editors

  • Dr. Yang Li Dr. Yang Li  &

    Dr. Yang Li

    Dr. Yang Li is an Associate Editor for journals “Precision Agriculture”, “Plant Methods”, and “Data Technologies and Applications”. Currently, he is an Associate Professor with the College of Mechanical and Electrical Engineering, Shihezi University, Shihezi, China. His recent research interests include machine learning, computer vision, information processing, IoT, data quality assessment. He has published over 60 research papers in the international reputed journals, such as IEEE TII, IoTJ, JSTARS, TNSE, TASE, TCSVT, IS. His research has been funded by the National Natural Science Foundation of China Shihezi University, China. Email:

  • Dr. Houbing Herbert Song Dr. Houbing Herbert Song

    Dr. Houbing Herbert Song

    Dr. Houbing Herbert Song is an IEEE Fellow, also acts as an Associate Editor for journals “IEEE Internet of Things Journal”, “IEEE Transactions on Intelligent Transportation Systems”, “IEEE Communications Magazine”, “IEEE Access”, etc. Currently, he is an Associate Professor with the Department of Information Systems, University of Maryland, Baltimore County (UMBC), USA. He is the Director of Security and Optimization for Networked Globe Laboratory (SONG Lab, www.SONGLab.us). He has published more than 300 technical articles. University of Maryland, Baltimore County (UMBC), USA. Email: h.song@ieee.org

Articles (4 in this collection)