Special Issue "Visual Learning with Multi-Task Supervision"

A special issue of Journal of Imaging (ISSN 2313-433X). This special issue belongs to the section "Visualization and Computer Graphics".

Deadline for manuscript submissions: 20 January 2023 | Viewed by 103

Special Issue Editor

Dr. Miaojing Shi
E-Mail Website
Guest Editor
Department of Informatics, King's College London, London WC2B 4BG, UK
Interests: computer vision; multimedia computing; medical imaging; few-shot learning; multi-task learning; self-supervised learning

Special Issue Information

Dear Colleagues,

Driven by the increasing availability of large-scale annotated datasets and faster computational platforms, deep learning has been progressively employed for a broader spectrum of computer vision applications. In some scenarios, one might find that a machine performs even better than a human. On the other hand, a human, though sometimes less proficient at performing certain tasks, can perform a broader range of tasks, superior to any existing computer vision algorithms.  To equip the machine perception with this ability, we need to study visual learning with multi-task supervision.

Multi-task learning is common in deep learning, where clear evidence shows that jointly learning correlated tasks can improve on individual performances. Notwithstanding many tasks are processed independently. The reasons are manifold: 1) many tasks are not strongly correlated, and benefits might be obtained for only one or none of the tasks in joint learning; 2) the scalability of learning multiple tasks is limited with the number of tasks. Establishing a scalable and robust multi-task learning strategy is of substantial potential in many real applications, i.e., autonomous vehicle, medical imaging, etc.

This Special Issue will push forward the current study in the multi-task visual learning. We welcome contributions focusing on high-level visual understanding tasks (e.g., object detection, semantic segmentation, etc.) and applicable scenarios (e.g., robotic surgery, autonomous driving, etc.).

Dr. Miaojing Shi
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 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. 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 1600 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-task learning
  • visual understanding
  • autonomous driving
  • medical imaging
  • robotic surgery

Published Papers

This special issue is now open for submission.
Back to TopTop