Machine Learning with Extremely Few Annotations for Remote Sensing
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: closed (25 December 2023) | Viewed by 3505
Special Issue Editors
Interests: domain adaptation; image classification; video tracking and detection
Interests: machine learning
Special Issue Information
Dear Colleagues,
Annotations are always required for both supervised/semi-supervised model training and evaluation. The quality of annotation largely influences the quality of the ML model. Manually annotating data (images, videos, etc.) is arduous and expensive, especially for remote sensing data. A recent trend for conducting such laborious annotation tasks is through crowdsourcing, where data are annotated by volunteers or paid workers online (e.g., workers of Amazon Mechanical Turk) from scratch. However, the quality of these crowdsourcing annotations cannot be guaranteed, and incompleteness and incorrectness are two major concerns for crowdsourcing annotations.
To address such concerns, this Special Issue is devoted to exploring the potential of novel machine learning ways with extremely few annotations. Further, authors might reflect on how to select the data to annotate given a certain annotation budget, as annotating different data might come with different difficulties, and data themselves might be of differing significance. An example of rethinking might be that if the annotators only partially annotate multilabel images with salient labels instead of fully annotating them, there will be fewer annotation errors, and a better trained ML model might be obtained with these annotated data.
Topics of interest include but are not limited to:
- Few-shot learning for remote sensing;
- Domain adaptation/transfer learning for remote sensing;
- Multilabel image classification/segmentation with partial annotations for remote sensing;
- Semi-supervised learning methods for remote sensing;
- Active learning for remote sensing;
- Domain generalization algorithms for visual problems;
- Deep representation learning for domain adaptation and generalization.
Dr. Jianzhe Lin
Dr. Renjing Xu
Dr. Donghao Zhang
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
- domain adaptation
- few-shot learning
- annotation budget
- active learning
- deep representation
- multi-label image classification
