Research map / Label-efficient and robust learning / Recognition and long-tail
Transfer Learning from Deep Features for Remote Sensing and Poverty Mapping
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Transfer ImageNet-pretrained VGG F features through nighttime-light training for poverty classification | VGG F features with logistic regression · Uganda LSMS | accuracy: 0.686 -> 0.716 | Helped |
| Transfer ImageNet-pretrained VGG F features through nighttime-light training for poverty classification | VGG F features with logistic regression · Uganda LSMS | F1 Score: 0.398 -> 0.489 | Helped |
| Transfer ImageNet-pretrained VGG F features through nighttime-light training for poverty classification | VGG F features with logistic regression · Uganda LSMS | Recall: 0.492 -> 0.658 | Mixed |
| Use nighttime-light-trained features instead of nighttime-light features directly | Poverty classification · Uganda LSMS | accuracy: 0.526 -> 0.716 | Helped |
| Evaluate overlapping image regions with a fully convolutional model rather than random cropping | VGG F nighttime-light predictor · Nighttime light prediction | validation accuracy: 70.04% -> 71.58% | Helped |
| Use fully convolutional evaluation rather than random cropping | VGG F nighttime-light predictor · Nighttime light prediction | training iterations to reported validation result: 400,200 -> 223,500 | Helped |
Closest papers by meaning
- Combining Deep Learning and Street View Imagery to Map Smallholder Crop Types (AAAI 2024 · similarity 0.87)
- HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing (AAAI 2024 · similarity 0.85)
- RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing (NeurIPS 2025 · similarity 0.84)
- UV-SAM: Adapting Segment Anything Model for Urban Village Identification (AAAI 2024 · similarity 0.84)
- SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing (AAAI 2024 · similarity 0.84)
- Large-Scale School Mapping Using Weakly Supervised Deep Learning for Universal School Connectivity (AAAI 2025 · similarity 0.84)
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.