Research map / Label-efficient and robust learning / Recognition and long-tail
Topological RANSAC for instance verification and retrieval without fine-tuning
Guoyuan An, Ju-hyeong Seon, Inkyu An, Yuchi Huo, Sung-eui Yoon
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 spatial verification with topological verification in RANSAC | SIFT-based image retrieval · ROxf Medium and Hard; ROxf+R1M Medium and Hard; RPar Medium and Hard; RPar+R1M Medium and Hard | mAP (%): 64 -> 69.5; 42 -> 46.9; 56.3 -> 60.4; 30.5 -> 34.4; 86.3 -> 86.5; 71.6 -> 71.6; 70.1 -> 70.6; 46.4 -> 46.8 | Improved |
| add SP filtering to the TP hypothesis set (ablation) | TP with SIFT · ROxf Medium and Hard; ROxf+R1M Medium and Hard; RPar Medium and Hard; RPar+R1M Medium and Hard | mAP (%): 69.5 -> 68.6; 46.9 -> 46.3; 60.4 -> 59.2; 34.4 -> 33.9; 86.5 -> 86.6; 71.6 -> 71.7; 70.6 -> 70.5; 46.8 -> 46.6 | Mixed |
| use TP instead of SP | Hypergraph Propagation retrieval · ROxford Medium, hop1 | mAP (%): 80 -> 81 | Improved |
| use TP instead of SP | Hypergraph Propagation retrieval · ROxford Hard, hop1 | mAP (%): 61 -> 63 | Improved |
| use TP instead of SP | Hypergraph Propagation retrieval · ROxford Medium, hop2 | mAP (%): 85 -> 86 | Improved |
| use TP instead of SP | Hypergraph Propagation retrieval · ROxford Hard, hop2 | mAP (%): 69 -> 71 | Improved |
Closest papers by meaning
- Learning Spatial-context-aware Global Visual Feature Representation for Instance Image Retrieval (ICCV 2023 · similarity 0.85)
- Guided Similarity Separation for Image Retrieval (NeurIPS 2019 · similarity 0.83)
- Explore-Exploit Graph Traversal for Image Retrieval (CVPR 2019 · similarity 0.83)
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (ICLR 2025 · similarity 0.82)
- Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning (NeurIPS 2026 · similarity 0.82)
- Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations (AAAI 2024 · similarity 0.82)
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.
