Deep Representation Learning in Remote Sensing
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "AI Remote Sensing".
Deadline for manuscript submissions: closed (1 April 2023) | Viewed by 2889
Special Issue Editors
Interests: generative adversarial networks; adversarial attacks; deep learning; statistical learning
Interests: representation learning; image retrieval; remote sensing
Interests: remote sensing; deep learning; land-cover mapping
Special Issue Information
Dear Colleagues,
The process of learning representations of data for the purpose of downstream tasks has received much attention in the last decade. In the field of computer vision, transfer learning has become a common practice, with representations learned on the ImageNet dataset often used as a starting point for fine-tuning. Remote sensing images differ from natural images in some crucial ways: they contain numerous objects as opposed to single subjects, they are often multispectral in nature, and they can also be treated as a time-series. As such, specific datasets and techniques are required for effective representation learning in remote sensing. Recent advances in self-supervised and semi-supervised learning show promise in label-scarce and data-rich settings; however, there have been few attempts to specifically adapt these approaches to remote sensing and leverage the inherent spectral, spatial, and temporal structure of remote sensing data.
The aim of this Special Issue is to present novel representation learning modalities, algorithms, and datasets for remote sensing imagery. Topics may cover any type of imagery (multispectral, hyperspectral, synthetic aperture radar, etc.) and downstream tasks (land-cover classification or mapping, change detection, time-series classification, etc.)
Suggested themes and article types for submissions:
- Self-supervised Learning for Transfer Learning;
- Semi-supervised Learning for Transfer Learning;
- Cross-modality Representation Learning;
- Change Detection;
- Land cover mapping;
- Object detection;
- Image retrieval;
- Sensor Fusion.
Dr. Christopher Xiang Ren
Dr. Michal Kucer
Krishna Karra
Dr. Alice M. S. Durieux
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. Remote Sensing 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 2700 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
- self-supervised learning
- representation learning
- semi-supervised learning
- transfer learning
- deep learning
- change detection
- land-cover mapping