Prompting a multimodal LLM to output a JSON similarity score directly, plus a mean-minus-standard-deviation consistency penalty, raises Tokyo247 R@1 from 77.1% (DINOv2 GeM) to 91.1% without fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time
Prompting a multimodal LLM to output a JSON similarity score directly, plus a mean-minus-standard-deviation consistency penalty, raises Tokyo247 R@1 from 77.1% (DINOv2 GeM) to 91.1% without fine-tuning.