Next Article in Journal
A Forest Monitoring System for Tanzania
Next Article in Special Issue
Integrated High-Definition Visualization of Digital Archives for Borobudur Temple
Previous Article in Journal
A Multi-Frequency Galileo PPP-RTK Convergence Analysis with an Emphasis on the Role of Frequency Spacing
 
 
Article

Connecting Images through Sources: Exploring Low-Data, Heterogeneous Instance Retrieval

1
LaSTIG, IGN-ENSG, Gustave Eiffel University, 77420 Champs-sur-Marne, France
2
LIRIS, École Centrale de Lyon, 69134 Écully, France
*
Author to whom correspondence should be addressed.
Academic Editors: Nikos Grammalidis, Kosmas Dimitropoulos and Anastasios Doulamis
Remote Sens. 2021, 13(16), 3080; https://doi.org/10.3390/rs13163080
Received: 31 May 2021 / Revised: 28 July 2021 / Accepted: 30 July 2021 / Published: 5 August 2021
(This article belongs to the Special Issue Digitization and Visualization in Cultural Heritage)
Along with a new volume of images containing valuable information about our past, the digitization of historical territorial imagery has brought the challenge of understanding and interconnecting collections with unique or rare representation characteristics, and sparse metadata. Content-based image retrieval offers a promising solution in this context, by building links in the data without relying on human supervision. However, while the latest propositions in deep learning have shown impressive results in applications linked to feature learning, they often rely on the hypothesis that there exists a training dataset matching the use case. Increasing generalization and robustness to variations remains an open challenge, poorly understood in the context of real-world applications. Introducing the alegoria benchmark, containing multi-date vertical and oblique aerial digitized photography mixed with more modern street-level pictures, we formulate the problem of low-data, heterogeneous image retrieval, and propose associated evaluation setups and measures. We propose a review of ideas and methods to tackle this problem, extensively compare state-of-the-art descriptors and propose a new multi-descriptor diffusion method to exploit their comparative strengths. Our experiments highlight the benefits of combining descriptors and the compromise between absolute and cross-domain performance. View Full-Text
Keywords: CBIR; cross-domain; cultural heritage; benchmarking; diffusion CBIR; cross-domain; cultural heritage; benchmarking; diffusion
Show Figures

Figure 1

MDPI and ACS Style

Gominski, D.; Gouet-Brunet, V.; Chen, L. Connecting Images through Sources: Exploring Low-Data, Heterogeneous Instance Retrieval. Remote Sens. 2021, 13, 3080. https://doi.org/10.3390/rs13163080

AMA Style

Gominski D, Gouet-Brunet V, Chen L. Connecting Images through Sources: Exploring Low-Data, Heterogeneous Instance Retrieval. Remote Sensing. 2021; 13(16):3080. https://doi.org/10.3390/rs13163080

Chicago/Turabian Style

Gominski, Dimitri, Valérie Gouet-Brunet, and Liming Chen. 2021. "Connecting Images through Sources: Exploring Low-Data, Heterogeneous Instance Retrieval" Remote Sensing 13, no. 16: 3080. https://doi.org/10.3390/rs13163080

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop