Proceedings of the 2021 International Conference on Multimedia Retrieval 2021
DOI: 10.1145/3460426.3463644
|View full text |Cite
|
Sign up to set email alerts
|

Leveraging EfficientNet and Contrastive Learning for Accurate Global-scale Location Estimation

Abstract: In this paper, we address the problem of global-scale image geolocation, proposing a mixed classification-retrieval scheme. Unlike other methods that strictly tackle the problem as a classification or retrieval task, we combine the two practices in a unified solution leveraging the advantages of each approach with two different modules. The first leverages the EfficientNet architecture to assign images to a specific geographic cell in a robust way. The second introduces a new residual architecture that is trai… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
11
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
2
2

Relationship

0
7

Authors

Journals

citations
Cited by 15 publications
(11 citation statements)
references
References 38 publications
0
11
0
Order By: Relevance
“…At test time, the trained model is used to extract image descriptors and perform a classic retrieval. While CosPlace might appear similar to previous classificationbased works [25,30,35,42,52], given that they also partition a map into classes, there are substantial differences. These prior works tackle the task of global classification and group images within very large cells (up to hundreds of kilometers wide), building on the idea that nearer scenes have similar semantics (e.g.…”
Section: Related Workmentioning
confidence: 75%
See 2 more Smart Citations
“…At test time, the trained model is used to extract image descriptors and perform a classic retrieval. While CosPlace might appear similar to previous classificationbased works [25,30,35,42,52], given that they also partition a map into classes, there are substantial differences. These prior works tackle the task of global classification and group images within very large cells (up to hundreds of kilometers wide), building on the idea that nearer scenes have similar semantics (e.g.…”
Section: Related Workmentioning
confidence: 75%
“…Visual geo-localization as classification. An alternative approach to visual geo-localization is to consider it a classification problem [25,30,35,42,52]. These works build on the idea that two images coming from the same geographical region, although representing different scenes, are likely to share similar semantics, such as architectural styles, types of vehicles, vegetation, etc.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…10, we show a more comprehensive set of results than in the main paper, comprising all the aggregation methods that can be attached to the different backbones using our software. As seen in the literature, GeM pooling [60] outperforms in general SPOC [5], MAC [62], R-MAC [71], RRM [39].…”
Section: C2 Aggregation and Descriptors Dimensionalitymentioning
confidence: 88%
“…Over the years, a number of such methods have been proposed, from shallow pooling layers [5,62] to more complex modules [2,37]. Our framework allows to compute results with a number of them, namely SPOC [5], MAC [62], R-MAC [71], RRM [39], GeM [60], NetVLAD [2] and CRN [37]. While a complete list of results with all aggregation methods is shown in Appendix C.2, in Tab.…”
Section: Aggregation and Descriptor Dimensionalitymentioning
confidence: 99%