Research map / Graph learning / Graph algorithms and clustering
Guided Similarity Separation for Image Retrieval
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 |
|---|---|---|---|
| Add spatial verification when building the training adjacency matrix (GSSV vs GSS) (ablation) | GeM+GSS · ROxford Hard | mAP: 57.5 -> 62.2 | Helped |
| Add spatial verification at query time on top of GSSV (ablation) | GeM+GSSV · ROxford Hard | mAP: 62.2 -> 64.7 | Helped |
| Add spatial verification at query time on top of GSSV (ablation) | GeM+GSSV · RParis Hard | mAP: 85.3 -> 85.3 | No clear effect |
| Replace GeM descriptors with GSS (GCN neighbor encoding plus pairwise separation loss) | GeM · ROxford Hard | mAP: 38.5 -> 57.5 | Helped |
| GSS vs best similarity propagation baseline (GeM+DSM+DFS) | GeM · RParis Hard | mAP: 79.3 -> 83.5 | Helped |
| Spatial verification at query time costs more inference time for more candidates (ablation) | GSSV-SV · ROxford Hard | run-time overhead: over 70% increase in run-time | Hurt |
Closest papers by meaning
- Scene Graph Embeddings Using Relative Similarity Supervision (AAAI 2021 · similarity 0.90)
- Explore-Exploit Graph Traversal for Image Retrieval (CVPR 2019 · similarity 0.89)
- SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval (ICML 2025 · similarity 0.89)
- Fast Spectral Ranking for Similarity Search (CVPR 2018 · similarity 0.89)
- Instance-Level Composed Image Retrieval (NeurIPS 2025 · similarity 0.87)
- Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval (ICLR 2025 · similarity 0.86)
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.
