Research map / Vision-language and multimodal / Cross-modal learning
LaVPR: Benchmarking Language and Vision for Place Recognition
Ofer Idan, Dan Badur, yosi keller, Yoli Shavit
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 learned projection (LLP) to ADS fusion (ablation) | MixVPR + BGE-L ADS · Amstertime | R@1: 36.1 -> 38.1 | Improved |
| add LLP to CAT fusion (ablation) | MixVPR + BGE-L CAT · Amstertime | R@1: 37.0 -> 30.2 | Hurt |
| add text descriptions via CAT fusion | MixVPR · Amstertime | R@1: 35.7 -> 37.0 | Improved |
| add text descriptions via CAT fusion | MixVPR · MSLS-val | R@1: 83.2 -> 81.9 | Hurt |
| add language (ADS+LLP) on blurred queries | MixVPR · MSLS-Blur | R@1: 70.9 -> 81.4 | Improved |
| add language (ADS+LLP) on weather queries | SALAD · MSLS-Weather | R@1: 90.7 -> 94.2 | Improved |
| add language to SSL DINOv2 backbone | SALAD / CricaVPR · Relative R@1 gain | R@1: <7% | Mixed |
| add language to supervised VGG NetVLAD | NetVLAD · Relative R@1 gain | R@1: 200% | Improved |
| use joint fusion instead of sequential re-ranking (ablation) | MixVPR + BGE · Amstertime | R@1: 1.2 -> 37.0 | Improved |
| add language to small ViT-S backbone | CricaVPR-Small · MSLS-Blur | R@1: 89.5 -> 93.0 | Improved |
| use LoRA instead of full fine-tuning (ablation) | BLIP with MS loss · Amstertime cross-modal | R@1: 0.1 -> 12.8 | Improved |
| use MS loss instead of contrastive loss (ablation) | BLIP LoRA all linear r=64 · Amstertime cross-modal | R@1: 0.1 -> 12.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CricaVPR — CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition (CVPR 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition (AAAI 2025 · similarity 0.89)
- DialogueVPR: Towards Conversational Visual Place Recognition (CVPR 2026 · similarity 0.89)
- ERGeoBench: A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models (ICML 2026 · similarity 0.88)
- MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering (NeurIPS 2025 · similarity 0.88)
- Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition (ICLR 2024 · similarity 0.88)
- EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition (ICLR 2025 · similarity 0.88)
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.
