paper-with-me

홈 › Papers

Learning to Interpret Satellite Images in Global Scale Using Wikipedia

2019-05-07 · Burak Uzkent, Evan Sheehan, Chenlin Meng, Zhongyi Tang, Marshall Burke, David Lobell, Stefano Ermon

Despite recent progress in computer vision, finegrained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we construct a novel dataset called WikiSatNet by pairing georeferenced Wikipedia articles with satellite imagery of their corresponding locations. We then propose two strategies to learn representations of satellite images by predicting properties of the corresponding articles from the images. Leveraging this new multi-modal dataset, we can drastically reduce the quantity of human-annotated labels and time required for downstream tasks. On the recently released fMoW dataset, our pre-training strategies can boost the performance of a model pre-trained on ImageNet by up to 4:5% in F1 score.

📄 PDF Abstract BibTeX arXiv:1905.02506

Code (3)

buzkent86/WikiSatNet pytorch
ermongroup/PretrainingWikiSatNet pytorch
uzkent/WikiSatNet pytorch

Tasks

Articles

Similar Papers 제목 키워드 기반

Learning to Interpret Satellite Images Using Wikipedia

2018-09-19 · Evan Sheehan, Burak Uzkent, Chenlin Meng, Zhongyi Tang 외

Despite recent progress in computer vision, fine-grained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we propose using Wikipedia as a pre…

Articles

Envisioning global urban development with satellite imagery and generative AI

2026-03-27 · Kailai Sun, Yuebing Liang, Mingyi He, Yunhan Zheng 외 arxiv

Urban development has been a defining force in human history, shaping cities for centuries. However, past studies mostly analyze such development as predictive tasks, failing to reflect its generative nature. Therefore, …

Building Detection from Satellite Images on a Global Scale

2017-07-27 · Amy Zhang, Xian-Ming Liu, Andreas Gros, Tobias Tiecke

In the last several years, remote sensing technology has opened up the possibility of performing large scale building detection from satellite imagery. Our work is some of the first to create population density maps from…

Density Estimation

FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stations

2022-02-02 · Jinhyun So, Kevin Hsieh, Behnaz Arzani, Shadi Noghabi 외

Large-scale deployments of low Earth orbit (LEO) satellites collect massive amount of Earth imageries and sensor data, which can empower machine learning (ML) to address global challenges such as real-time disaster navig…

Federated Learning

Deep Learning Based Large-Scale Automatic Satellite Crosswalk Classification

2017-06-28 · Rodrigo F. Berriel, Andre Teixeira Lopes, Alberto F. de Souza, Thiago Oliveira-Santos

High-resolution satellite imagery have been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Even though, very little effort has been placed o…

ClassificationDeep LearningGeneral Classification