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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use a GCN with CNN image embeddings instead of the strongest object-count model | Livelihood prediction · India wealth | accuracy: 75.77 -> 81.06 | Improved |
| Use a GCN with CNN embeddings and object counts instead of the strongest object-count model | Livelihood prediction · India wealth | r^2: 0.52 -> 0.53 | Improved |
| Use a GCN with CNN image embeddings instead of image-wise ResNet | Livelihood prediction · India population | accuracy: 93.50 -> 94.71 | Improved |
| Use a GCN with CNN embeddings and object counts instead of image-wise ResNet | Livelihood prediction · India population | r^2: 0.85 -> 0.89 | Improved |
| Use a GCN with CNN embeddings and object counts instead of image-wise ResNet | Livelihood prediction · India women's BMI | accuracy: 85.28 -> 89.56 | Improved |
| Use a GCN with CNN image embeddings instead of the strongest object-count model | Livelihood prediction · India women's BMI | r^2: 0.54 -> 0.57 | Improved |
| Use a GCN with CNN image embeddings instead of the strongest object-count model | Livelihood prediction · Kenya wealth | accuracy: 77.34 -> 76.06 | Hurt |
| Use a GCN with CNN image embeddings instead of the strongest object-count model | Livelihood prediction · Kenya wealth | r^2: 0.50 -> 0.42 | Hurt |
| Use a GCN with CNN image embeddings instead of the strongest object-count model | Livelihood prediction · Kenya population | accuracy: 89.59 -> 89.67 | Improved |
| Use a GCN with CNN embeddings and object counts instead of image-wise ResNet | Livelihood prediction · Kenya population | r^2: 0.90 -> 0.85 | Hurt |
Closest papers by meaning
- CityLens: Evaluating Large Vision-Language Models for Urban Socioeconomic Sensing (ICLR 2026 · similarity 0.85)
- UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction (AAAI 2025 · similarity 0.85)
- Combining Deep Learning and Street View Imagery to Map Smallholder Crop Types (AAAI 2024 · similarity 0.84)
- HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing (AAAI 2024 · similarity 0.84)
- UV-SAM: Adapting Segment Anything Model for Urban Village Identification (AAAI 2024 · similarity 0.84)
- Flood Insights: Integrating Remote and Social Sensing Data for Flood Exposure, Damage, and Urgent Needs Mapping (AAAI 2024 · similarity 0.81)
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.
