AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Tile2Vec: Unsupervised Representation Learning for Spatially Distributed Data

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

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learn embeddings from geographically neighboring and distant tile tripletsTile2Vec on CDL land cover classification · CDL land cover classification, n=1000accuracy: Tile2Vec: 52.6 ± 1.1; Autoencoder: 49.1 ± 0.7Improved
learn embeddings from geographically neighboring and distant tile tripletsTile2Vec on CDL land cover classification · CDL land cover classification, n=10000accuracy: Tile2Vec: 59.7 ± 0.3; Autoencoder: 55.6 ± 0.2Improved
learn Tile2Vec embeddings from Landsat imageryUganda poverty prediction · Uganda LSMSr^2: 0.41 -> 0.496 ± 0.014Improved
learn Tile2Vec embeddings from non-health country features using spatial tripletsCountry health index prediction · CIA Factbook countriesr^2: kNN: 62.8 ± 1.5 -> 77.5 ± 1.0; RF: 72.1 ± 1.6 -> 76.0 ± 1.3; RR: 68.7 ± 1.7 -> 69.6 ± 1.0Improved
use neighborhood radius 100 instead of sampling tiles without a neighborhood constraint (ablation)Tile2Vec, tile size 100, LR · CDL land cover classificationaccuracy: 35.2 ± 0.0 -> 61.8 ± 0.4Improved
increase neighborhood radius from 100 to 1000 pixels (ablation)Tile2Vec on NAIP · CDL land cover classificationaccuracy: 61.8 ± 0.4 -> 55.1 ± 0.4Hurt
vary the triplet-loss margin from 0.1 to 100 (ablation)Tile2Vec on NAIP · CDL land cover classificationaccuracyNo clear effect
remove embedding-magnitude regularization (ablation)Tile2Vec · CDL land cover classificationfeature qualityNo clear effect
increase tile size (ablation)Tile2Vec on NAIP · CDL land cover classificationaccuracy: At neighborhood 100, LR: 57.8 ± 0.4 -> 61.8 ± 0.4 (tile size 25 to 100)Improved

Later papers that compared with this method

1 later accepted paper reports Tile2Vec as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy