Jain Pallavi, Marcos Diego, Ienco Dino, Interdonato Roberto, Dhakal Aayush, Jacobs Nathan, Berchoux Tristan.
2024. Aligning geo-tagged clip representations and satellite imagery for few-shot land use classification.
In : IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium. IEEE
![[img]](http://agritrop.cirad.fr/style/images/fileicons/text.png) |
Version post-print
- Anglais
Accès réservé aux personnels Cirad Utilisation soumise à autorisation de l'auteur ou du Cirad. 611807.pdf Télécharger (859kB) | Demander une copie |
Résumé : A major difference between ground-level and satellite imagery of landscapes lies in their semantic granularity: ground-level images tend to offer details on objects and human activities, while satellite images provide broader geographic context but, typically, with coarser semantics. This study aims to leverage this complementary information by integrating fine-grained insights from a ground-level view into the analysis of satellite image data. To achieve this integration, we propose to align a satellite image representation with co-located geo-tagged ground-level image CLIP representations. This method focuses on enriching satellite image visual features by leveraging the inherent visual characteristics found in ground-level images as a reference in a contrastive manner, without relying on additional textual information to guide the learning process. We evaluate the quality of the learned representations on the EuroSAT benchmark in various few-shot settings.
Mots-clés libres : Computer vision, Satellite image, Land use, Contrastive learning
Agences de financement européennes : European Commission
Programme de financement européen : Horizon Europe
Auteurs et affiliations
- Jain Pallavi, CIHEAM (FRA)
- Marcos Diego, INRIA (FRA)
- Ienco Dino, INRAE (FRA)
-
Interdonato Roberto, CIRAD-ES-UMR TETIS (FRA)
ORCID: 0000-0002-0536-6277
- Dhakal Aayush, Washington University in St Louis (USA)
- Jacobs Nathan, Washington University in St Louis (USA)
- Berchoux Tristan, CIRAD-ES-UMR TETIS (FRA)
Source : Cirad-Agritrop (https://agritrop.cirad.fr/611807/)
[ Page générée et mise en cache le 2025-02-03 ]
