Research map / Label-efficient and robust learning / Recognition and long-tail
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
Gabriele Berton, Gabriele Trivigno, 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 |
|---|---|---|---|
| add frontal loss to lateral loss (ablation) | EigenPlaces · Average of Pitts30k, Tokyo 24/7, MSLS Val, St Lucia | Recall@1: 87.6 -> 89.5 | Improved |
| add lateral loss to frontal loss (ablation) | EigenPlaces · Average of 4 datasets | Recall@1: 88.2 -> 89.5 | Improved |
| frontal loss only on multi-view datasets (ablation) | EigenPlaces · Tokyo 24/7 | Recall@1: 80.0 -> 78.1 | Hurt |
| increase focal distance from 0 to 10 m (ablation) | EigenPlaces · Average of 4 datasets | Recall@1: 86.1 -> 89.5 | Improved |
| increase focal distance from 10 to 20 m (ablation) | EigenPlaces · Average of 4 datasets | Recall@1: 89.5 -> 90.1 | Improved |
| increase focal distance beyond 20 m (ablation) | EigenPlaces · Average of 4 datasets | Recall@1: 90.1 -> 89.4 (30 m), 89.9 (50 m) | No clear effect |
| use EigenPlaces instead of CosPlace at 2048-D | ResNet-50 · SF-XL test v1 | Recall@1: 76.4 -> 84.1 | Improved |
| use EigenPlaces instead of MixVPR on frontal-view datasets | ResNet-50 · Nordland | Recall@1: 76.2 (MixVPR 4096-D) vs 71.2 (EigenPlaces 2048-D) | Hurt |
Closest papers by meaning
- EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition (ICLR 2025 · similarity 0.89)
- BoQ: A Place is Worth a Bag of Learnable Queries (CVPR 2024 · similarity 0.88)
- MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering (NeurIPS 2025 · similarity 0.88)
- Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era (NeurIPS 2025 · similarity 0.87)
- Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition (AAAI 2025 · similarity 0.87)
- DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition (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.
