AI Paper Atlas

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

Predicting Livelihood Indicators from Community-Generated Street-Level Imagery

Jihyeon Lee, Dylan Grosz, Burak Uzkent, Sicheng Zeng, Marshall Burke, David Lobell, Stefano Ermon

AAAI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 19 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
Use a GCN with CNN image embeddings instead of the strongest object-count modelLivelihood prediction · India wealthaccuracy: 75.77 -> 81.06Improved
Use a GCN with CNN embeddings and object counts instead of the strongest object-count modelLivelihood prediction · India wealthr^2: 0.52 -> 0.53Improved
Use a GCN with CNN image embeddings instead of image-wise ResNetLivelihood prediction · India populationaccuracy: 93.50 -> 94.71Improved
Use a GCN with CNN embeddings and object counts instead of image-wise ResNetLivelihood prediction · India populationr^2: 0.85 -> 0.89Improved
Use a GCN with CNN embeddings and object counts instead of image-wise ResNetLivelihood prediction · India women's BMIaccuracy: 85.28 -> 89.56Improved
Use a GCN with CNN image embeddings instead of the strongest object-count modelLivelihood prediction · India women's BMIr^2: 0.54 -> 0.57Improved
Use a GCN with CNN image embeddings instead of the strongest object-count modelLivelihood prediction · Kenya wealthaccuracy: 77.34 -> 76.06Hurt
Use a GCN with CNN image embeddings instead of the strongest object-count modelLivelihood prediction · Kenya wealthr^2: 0.50 -> 0.42Hurt
Use a GCN with CNN image embeddings instead of the strongest object-count modelLivelihood prediction · Kenya populationaccuracy: 89.59 -> 89.67Improved
Use a GCN with CNN embeddings and object counts instead of image-wise ResNetLivelihood prediction · Kenya populationr^2: 0.90 -> 0.85Hurt

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