Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Tile2Vec: Unsupervised representation learning for spatially distributed data

About

Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we introduce Tile2Vec, an unsupervised representation learning algorithm that extends the distributional hypothesis from natural language -- words appearing in similar contexts tend to have similar meanings -- to spatially distributed data. We demonstrate empirically that Tile2Vec learns semantically meaningful representations on three datasets. Our learned representations significantly improve performance in downstream classification tasks and, similar to word vectors, visual analogies can be obtained via simple arithmetic in the latent space.

Neal Jean, Sherrie Wang, Anshul Samar, George Azzari, David Lobell, Stefano Ermon• 2018

Related benchmarks

TaskDatasetResultRank
Image ClassificationEuroSAT
Accuracy73.39
569
Socio-economic indicator estimationCambodia socio-economic dataset
RMSE (POP)0.954
11
Socio-economic indicator estimationVietnam socio-economic dataset
RMSE (GRDP)0.875
11
Socio-economic indicator estimationSouth Korea socio-economic dataset
RMSE (GRDP)1.342
11
Socioeconomic indicator estimationVietnam (test)
GRDP0.418
11
Socioeconomic indicator estimationSouth Korea (test)
GRDP Estimate Score32.7
11
Socioeconomic indicator estimationCambodia (test)
POP0.621
11
ClassificationCashewPlant
Accuracy34.4
8
ClassificationBEN V2
Accuracy54.95
8
ClassificationS4A-tiles
Accuracy35.2
8
Showing 10 of 13 rows

Other info

Follow for update