Research map / Image generation / Super-resolution
Lightweight and Robust Representation of Economic Scales from Satellite Imagery
Sungwon Han, Donghyun Ahn, Hyunji Cha, Jeasurk Yang, Sungwon Park, Meeyoung Cha
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 READ's fixed-length summaries of satellite-image features instead of JMOP's summarizing approach | JMOP · South Korea population density | R-squared: 0.8985±0.0253 -> 0.9617±0.0090 | Improved |
| Transfer knowledge from the custom urban/rural labeled dataset | No-Proxy · South Korea population density | R-squared: 0.7359±0.1117 -> 0.9617±0.0090 | Improved |
| Add the mean statistic μ (ablation) | READ · South Korea population density | R-squared: 0.9429±0.0155 -> 0.9617±0.0090 | Improved |
| Add the correlation statistic ρ (ablation) | READ · South Korea population density | R-squared: 0.9527±0.0140 -> 0.9617±0.0090 | Improved |
| Add the image-count statistic n (ablation) | READ · South Korea population density | R-squared: 0.9579±0.0119 -> 0.9617±0.0090 | Improved |
| Add the standard-deviation statistic σ (ablation) | READ · South Korea population density | R-squared: 0.9586±0.0130 -> 0.9617±0.0090 | Improved |
| Replace ResNet18 with DenseNet121 as the backbone (ablation) | READ · South Korea population density | R-squared: 0.9617 -> 0.9337 | Hurt |
| Replace ResNet18 with AlexNet as the backbone (ablation) | READ · South Korea population density | R-squared: 0.9617 -> 0.9364 | Hurt |
| Replace ResNet18 with VGG16 as the backbone (ablation) | READ · South Korea population density | R-squared: 0.9617 -> 0.9407 | Hurt |
| Apply the South Korea-trained model to Vietnam without Vietnam-specific retraining | READ · Vietnam population density | R-squared: 0.8863 | Improved |
| Add Vietnam-specific custom labels and retrain (ablation) | READ · Vietnam population density | R-squared: 0.8863 -> 0.8876 | No clear effect |
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)
- Measuring Fine-Grained Urban Air Temperature with Satellite Imagery (AAAI 2025 · similarity 0.84)
- Scale-aware Recognition in Satellite Images under Resource Constraints (ICLR 2025 · similarity 0.84)
- DiffusionSat: A Generative Foundation Model for Satellite Imagery (ICLR 2024 · similarity 0.83)
- UV-SAM: Adapting Segment Anything Model for Urban Village Identification (AAAI 2024 · similarity 0.83)
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.
