Research map / Detection and segmentation / CNN features
Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-Localization
Gabriele Trivigno, Gabriele Berton, Juan Aragon, Barbara Caputo, Carlo Masone
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 cross-entropy linear classifiers with angular margin (AAMC) classifiers (ablation) | D&C · SF-XL | LR@1: 48.2 -> 61.4 | Improved |
| pipe D&C top-100 cells into CosPlace retrieval | CosPlace · SF-XL test v1 | LR@1: 65.9 -> 71.4 | Improved |
| pipe D&C top-10 cells into NetVLAD retrieval | NetVLAD · SF-XL test v1 | LR@1: 40.0 -> 62.6 | Improved |
| filter retrieval with HGE or CPlaNet classes instead of D&C | CosPlace · SF-XL test v1 | LR@1: 65.9 -> 52.7 (HGE, Top-100) | Hurt |
| use D&C top-1 cell only for retrieval filtering (ablation) | CosPlace · SF-XL test v1 | LR@1: 65.9 -> 57.0 | Hurt |
| use ANN search (HNSW) instead of exhaustive kNN for CosPlace | CosPlace · SF-XL test v1 | LR@1: 64.7 -> 52.5 | Hurt |
| use more than 4 classifiers or a single group (N=1) in the class partition (ablation) | D&C · SF-XL | LR@1 | Hurt |
| increase cell size from 20 m to 50 m or 100 m (ablation) | D&C · SF-XL | LR@1 | Hurt |
| apply D&C classification to small datasets (Pitts30k, Tokyo 24/7) | D&C · Pitts30k and Tokyo 24/7 | LR@1: LR@1 lower than 50% versus over 80% recall@1 for retrieval | Hurt |
Closest papers by meaning
- CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps (ECCV 2018 · similarity 0.90)
- Scaling Image Geo-Localization to Continent Level (NeurIPS 2025 · similarity 0.88)
- Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition (AAAI 2025 · similarity 0.88)
- Optimal Transport Aggregation for Visual Place Recognition (CVPR 2024 · similarity 0.87)
- GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization (NeurIPS 2025 · similarity 0.87)
- MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering (NeurIPS 2025 · 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.
