Progressive knowledge augmentation with VLM-extracted pattern descriptions improves marine mammal spectrogram classification over vanilla VLMs (25.4% vs 13.2%) while keeping models retraining-free.
Title resolution pending
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
-
Knowledge-Augmented Vision Language Models for Underwater Bioacoustic Spectrogram Analysis
Progressive knowledge augmentation with VLM-extracted pattern descriptions improves marine mammal spectrogram classification over vanilla VLMs (25.4% vs 13.2%) while keeping models retraining-free.