Research map / 3D vision / Depth and stereo
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
Sixing Hu, Mengdan Feng, Rang M. H. Nguyen, Gim Hee Lee
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 |
|---|---|---|---|
| Replace the retrieval architecture with CVM-Net-I using NetVLAD and weighted soft-margin loss | Ground-to-aerial retrieval · Vo and Hays (Denver) | Recall @top 1%: 59.9% -> 67.9% | Improved |
| Replace the retrieval architecture with CVM-Net-I using NetVLAD and weighted soft-margin loss | Ground-to-aerial retrieval · CVUSA | Recall @top 1%: 63.7% -> 91.4% | Improved |
| Use independent rather than shared NetVLAD weights (ablation) | CVM-Net · Vo and Hays (Denver) | Recall @top 1%: 66.6% -> 67.9% | Improved |
| Use independent rather than shared NetVLAD weights (ablation) | CVM-Net · CVUSA | Recall @top 1%: 87.2% -> 91.4% | Improved |
| Use VGG16 instead of AlexNet for local feature extraction (ablation) | CVM-Net-I with triplet loss · CVUSA | Recall @top 1%: 65.4% -> 91.4% | Improved |
| Use VGG16 instead of AlexNet for local feature extraction (ablation) | CVM-Net-II with triplet loss · CVUSA | Recall @top 1%: 63.0% -> 87.2% | Improved |
| Add quadruplet-loss terms to the triplet objective (ablation) | CVM-Net-I with AlexNet · CVUSA | Recall @top 1%: 65.4% -> 73.7% | Improved |
| Add quadruplet-loss terms to the triplet objective (ablation) | CVM-Net-II with AlexNet · CVUSA | Recall @top 1%: 63.0% -> 83.9% | Improved |
| Add quadruplet-loss terms to the triplet objective (ablation) | CVM-Net-I with VGG16 · CVUSA | Recall @top 1%: 91.4% -> 89.9% | Hurt |
| Add quadruplet-loss terms to the triplet objective (ablation) | CVM-Net-II with VGG16 · CVUSA | Recall @top 1%: 87.2% -> 88.7% | Improved |
| Replace triplet loss with contrastive loss (ablation) | CVM-Net-I · CVUSA | Recall @top 1%: 91.4% -> 87.8% | Hurt |
| Replace triplet loss with contrastive loss (ablation) | CVM-Net-II · CVUSA | Recall @top 1%: 87.2% -> 79.8% | Hurt |
Closest papers by meaning
- Lending Orientation to Neural Networks for Cross-View Geo-Localization (CVPR 2019 · similarity 0.92)
- Image-Based Geo-Localization Using Satellite Imagery (IJCV 2019 · similarity 0.91)
- Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization (NeurIPS 2019 · similarity 0.91)
- From Coarse to Fine: A Matching and Alignment Framework for Unsupervised Cross-View Geo-Localization (AAAI 2025 · similarity 0.89)
- Game4Loc: A UAV Geo-Localization Benchmark from Game Data (AAAI 2025 · similarity 0.87)
- Aligning Geometric Spatial Layout in Cross-View Geo-Localization via Feature Recombination (AAAI 2024 · similarity 0.87)
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.
