Research map / Graph learning / Graph algorithms and clustering
Explore-Exploit Graph Traversal for Image Retrieval
Check 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 |
|---|---|---|---|
| Add explore-exploit graph traversal to R-MAC retrieval | R-MAC · ROxford Hard | mAP: 32.4 -> 56.3 | Helped |
| Add explore-exploit graph traversal to R-MAC | R-MAC · RParis+R1M Hard | mAP: 59.4 -> 63.7 | Helped |
| Add explore-exploit graph traversal to R-MAC | R-MAC · RParis+R1M Hard | mAP: 70.4 -> 63.7 | Hurt |
| Add RANSAC edge reweighting to EGT (ablation) | R-MAC+EGT · ROxford Hard | mAP: 56.3 -> 65.8 | Helped |
| Add RANSAC edge reweighting to EGT (ablation) | R-MAC+QE+SV+EGT · ROxford Hard | mAP: 61.7 -> 65.8 | Helped |
| Add RANSAC edge reweighting to EGT (ablation) | R-MAC+QE+SV+EGT · RParis Hard | mAP: 81.2 -> 84.6 | Helped |
| Add EGT to query expansion and spatial verification (ablation) | R-MAC+QE+SV · ROxford Hard | mAP: 46.2 -> 61.7 | Helped |
| Add EGT to query expansion and spatial verification (ablation) | R-MAC+QE+SV · RParis Hard | mAP: 64.8 -> 81.2 | Helped |
| Use EGT with R-MAC without RANSAC reweighting | R-MAC · ROxford+R1M Medium | mAP: 55.6 -> 55.8 | No clear effect |
Closest papers by meaning
- Guided Similarity Separation for Image Retrieval (NeurIPS 2019 · similarity 0.89)
- Link and Code: Fast Indexing With Graphs and Compact Regression Codes (CVPR 2018 · similarity 0.89)
- Hypergraph Propagation and Community Selection for Objects Retrieval (NeurIPS 2021 · similarity 0.87)
- SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval (ICML 2025 · similarity 0.87)
- MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions (ICML 2024 · similarity 0.86)
- Instance-Level Composed Image Retrieval (NeurIPS 2025 · similarity 0.85)
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.