Fine-tuning BLIP-2 with LoRA on about 1,000 annotated indoor images improves generated navigation instructions, though the gains rest on an ad hoc, underspecified evaluation metric.
Parameter-efficient transfer learning for nlp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Fine-Tuning Vision-Language Models for Visual Navigation Assistance
Fine-tuning BLIP-2 with LoRA on about 1,000 annotated indoor images improves generated navigation instructions, though the gains rest on an ad hoc, underspecified evaluation metric.