Special Issue "Deep Learning from Multi-Sourced Data"
A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".
Deadline for manuscript submissions: closed (31 May 2023) | Viewed by 6308
Special Issue Editors
Interests: computer vision; machine learning; deep learning; video and image processing
Interests: multimedia signal processing; pattern recognition; machine learning; multimedia networking; statistical pattern recognition
Special Issue Information
Dear Colleagues,
With the fast development of deep learning technologies, vast quantities of data are usually required for deep model training. It is worth employing complementary and rich information from multiple sourced datasets when a single dataset can not meet the demand. However, several challenges remain in the learning of multi-sourced data. Firstly, multi-sourced data can have different modalities. Combining information from multi-modality data is usually difficult. Secondly, label inconsistency is another major issue. Some data samples are annotated with fine labels, while some have weak labels or in some cases no labels. Thirdly, there are annotation biases among different annotators, resulting in noisy label problems. Fourthly, domain gaps usually exist in multi-sourced data. Despite these challenges, there is a high demand for practical applications related to multi-sourced data, such as federated learning, distributed learning, multi-sensor fusion techniques, etc. As a result, learning from multi-sourced data is garnering more and more attention. In this Special Issue, we welcome original research, applications, and review articles in all areas related to learning from multi-sourced data.
Dr. Gaoang Wang
Prof. Dr. Jenq-Neng Hwang
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. Applied Sciences 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 2300 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
- multi-sourced learning
- multi-modality fusion
- federated learning
- noisy label
- doman adaptation