Research map / Detection and segmentation / Open-set and few-shot detection
Cataloging Public Objects Using Aerial and Street-Level Images - Urban Trees
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 |
|---|---|---|---|
| Combine aerial and street-view detections with map data and spatial context | det2geo · Pasadena Urban Trees | mAP: .42 -> .706 | Helped |
| Combine aerial and street-view features at three zoom levels | geo2cat · Pasadena Urban Trees | average precision: ≈.70 -> .80 | Helped |
| Combine aerial and street-view features at three zoom levels | geo2cat · Pasadena Urban Trees | average recall: .79 average recall | Helped |
| Add aerial-view information (ablation) | det2geo · Pasadena Urban Trees | mAP: .619 -> .706 | Helped |
| Add street-view information (ablation) | det2geo · Pasadena Urban Trees | mAP: .462 -> .706 | Helped |
| Add map potential (ablation) | det2geo · Pasadena Urban Trees | mAP: .667 -> .706 | Helped |
| Use learned spatial context instead of non-maximal suppression (ablation) | det2geo · Pasadena Urban Trees | mAP: .69 -> .706 | Helped |
| Learn scaling factors for the potential terms (ablation) | det2geo · Pasadena Urban Trees | mAP: .66 -> .706 | Helped |
Closest papers by meaning
- OAM-TCD: A globally diverse dataset of high-resolution tree cover maps (NeurIPS 2024 · similarity 0.86)
- UrbanDataLayer: A Unified Data Pipeline for Urban Science (NeurIPS 2024 · similarity 0.85)
- OpenStreetView-5M: The Many Roads to Global Visual Geolocation (CVPR 2024 · similarity 0.85)
- ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images (CVPR 2025 · similarity 0.83)
- WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification (CVPR 2024 · similarity 0.83)
- USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset (NeurIPS 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.