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).

Special Issue Editor

Dr. Tomas Skopal
E-Mail Website
Guest Editor
Department of Software Engineering, Charles University, Prague, Czech Republic
Interests: multimedia retrieval; database systems; machine learning

Special Issue Information

Dear Colleagues,

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
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 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.

Keywords

  • image retrieval
  • transfer learning
  • deep learning
  • data visualization
  • deep convolutional neural networks
  • pre-trained models

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Improved Visual Localization via Graph Filtering
J. Imaging 2021, 7(2), 20; https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging7020020 - 30 Jan 2021
Viewed by 511
Abstract
Vision-based localization is the problem of inferring the pose of the camera given a single image. One commonly used approach relies on image retrieval where the query input is compared against a database of localized support examples and its pose is inferred with [...] Read more.
Vision-based localization is the problem of inferring the pose of the camera given a single image. One commonly used approach relies on image retrieval where the query input is compared against a database of localized support examples and its pose is inferred with the help of the retrieved items. This assumes that images taken from the same places consist of the same landmarks and thus would have similar feature representations. These representations can learn to be robust to different variations in capture conditions like time of the day or weather. In this work, we introduce a framework which aims at enhancing the performance of such retrieval-based localization methods. It consists in taking into account additional information available, such as GPS coordinates or temporal proximity in the acquisition of the images. More precisely, our method consists in constructing a graph based on this additional information that is later used to improve reliability of the retrieval process by filtering the feature representations of support and/or query images. We show that the proposed method is able to significantly improve the localization accuracy on two large scale datasets, as well as the mean average precision in classical image retrieval scenarios. Full article
(This article belongs to the Special Issue Image Retrieval in Transfer Learning)
Show Figures

Figure 1

Article
Olympic Games Event Recognition via Transfer Learning with Photobombing Guided Data Augmentation
J. Imaging 2021, 7(2), 12; https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging7020012 - 20 Jan 2021
Viewed by 774
Abstract
Automatic event recognition in sports photos is both an interesting and valuable research topic in the field of computer vision and deep learning. With the rapid increase and the explosive spread of data, which is being captured momentarily, the need for fast and [...] Read more.
Automatic event recognition in sports photos is both an interesting and valuable research topic in the field of computer vision and deep learning. With the rapid increase and the explosive spread of data, which is being captured momentarily, the need for fast and precise access to the right information has become a challenging task with considerable importance for multiple practical applications, i.e., sports image and video search, sport data analysis, healthcare monitoring applications, monitoring and surveillance systems for indoor and outdoor activities, and video captioning. In this paper, we evaluate different deep learning models in recognizing and interpreting the sport events in the Olympic Games. To this end, we collect a dataset dubbed Olympic Games Event Image Dataset (OGED) including 10 different sport events scheduled for the Olympic Games Tokyo 2020. Then, the transfer learning is applied on three popular deep convolutional neural network architectures, namely, AlexNet, VGG-16 and ResNet-50 along with various data augmentation methods. Extensive experiments show that ResNet-50 with the proposed photobombing guided data augmentation achieves 90% in terms of accuracy. Full article
(This article belongs to the Special Issue Image Retrieval in Transfer Learning)
Show Figures

Figure 1

Article
Use of Very High Spatial Resolution Commercial Satellite Imagery and Deep Learning to Automatically Map Ice-Wedge Polygons across Tundra Vegetation Types
J. Imaging 2020, 6(12), 137; https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging6120137 - 11 Dec 2020
Cited by 12 | Viewed by 1277
Abstract
We developed a high-throughput mapping workflow, which centers on deep learning (DL) convolutional neural network (CNN) algorithms on high-performance distributed computing resources, to automatically characterize ice-wedge polygons (IWPs) from sub-meter resolution commercial satellite imagery. We applied a region-based CNN object instance segmentation algorithm, [...] Read more.
We developed a high-throughput mapping workflow, which centers on deep learning (DL) convolutional neural network (CNN) algorithms on high-performance distributed computing resources, to automatically characterize ice-wedge polygons (IWPs) from sub-meter resolution commercial satellite imagery. We applied a region-based CNN object instance segmentation algorithm, namely the Mask R-CNN, to automatically detect and classify IWPs in North Slope of Alaska. The central goal of our study was to systematically expound the DLCNN model interoperability across varying tundra types (sedge, tussock sedge, and non-tussock sedge) and image scene complexities to refine the understanding of opportunities and challenges for regional-scale mapping applications. We corroborated quantitative error statistics along with detailed visual inspections to gauge the IWP detection accuracies. We found promising model performances (detection accuracies: 89% to 96% and classification accuracies: 94% to 97%) for all candidate image scenes with varying tundra types. The mapping workflow discerned the IWPs by exhibiting low absolute mean relative error (AMRE) values (0.17–0.23). Results further suggest the importance of increasing the variability of training samples when practicing transfer-learning strategy to map IWPs across heterogeneous tundra cover types. Overall, our findings demonstrate the robust performances of IWPs mapping workflow in multiple tundra landscapes. Full article
(This article belongs to the Special Issue Image Retrieval in Transfer Learning)
Show Figures

Figure 1

Back to TopTop