A cosine-consistency voting scheme with a domain-adapted embedding raises VLM accuracy on maize disease diagnosis by 5.6 to 15.5 percentage points, but the gain is measured with the same LLM scorer used to create the training labels.
maize leaf blight, severe infection symp- toms: tan to grayish spots with darker borders, analysis: se- vere tan spots require mancozeb
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
-
Self-Consistency in Vision-Language Models for Precision Agriculture: Multi-Response Consensus for Crop Disease Management
A cosine-consistency voting scheme with a domain-adapted embedding raises VLM accuracy on maize disease diagnosis by 5.6 to 15.5 percentage points, but the gain is measured with the same LLM scorer used to create the training labels.