VICP uses an LLM to generate per-category visual prompts for a frozen DINOv2, enabling few-shot generalization to unseen object categories in re-identification without parameter updates.
Learning local feature descriptors with triplets and shallow convolutional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generalizable Object Re-Identification via Visual In-Context Prompting
VICP uses an LLM to generate per-category visual prompts for a frozen DINOv2, enabling few-shot generalization to unseen object categories in re-identification without parameter updates.