Work

Tile2Vec: Unsupervised representation learning for remote sensing data

Year: 2018
Type: article
Abstract: 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 for both image and non-image datasets. Our learned representations significantly improve performance in downstream classification tasks and, similarly to word vectors, allow visual analogies to be obtained via simple arithmetic in the latent space.
Institution: Stanford University
Language: English
Open Access status: green
OpenAlex ID: W2964246847
FWCI: 7.107
Cites: 26
Cited by: 210
Related to: 9