Special Issue "Image Retrieval in Transfer Learning"
A special issue of Journal of Imaging (ISSN 2313-433X).
Deadline for manuscript submissions: closed (30 November 2020).
In recent years, we have witnessed the revolution that deep learning brought to the world of artificial intelligence. In particular, the best models for general image retrieval are nowadays based on features produced by deep convolutional neural networks (DCNN). However, this tremendous success came with a high cost: the necessity of gathering exhaustive amounts of labeled data, followed by designing and training models. On the other hand, transfer-learning approaches that bypass this costly step by an application of pre-trained and fine-tuned generic DCNN models on completely different data domains have been developed. This Special Issue is especially devoted to novel methods of transfer learning that transform domain-specific retrieval problems into general image retrieval by pre-trained DCNN models. The key step in such a transformation is usually the visualization of the source data (even non-visual) into artificial images the visual features of which match to some extent the learned deep features within a generic DCNN model. Recent contributions to this concept include narrow-domain image classification, audio retrieval, biometric, bioinformatics and biomedicine applications, to name a few. We encourage authors to submit novel papers that generally use transfer learning techniques in image retrieval or, specifically, transform non-visual data into the visual domain and apply transfer learning by means of pre-trained DCNN models.
Dr. Tomas Skopal
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 papers will be 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.
- image retrieval
- transfer learning
- deep learning
- data visualization
- deep convolutional neural networks
- pre-trained models