A fine-tuned vision-language model with one in-context example classifies product defects with 0.804 MCC on MVTec AD without per-product retraining, though the evaluation protocol needs scrutiny.
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
REJECT 1representative citing papers
citing papers explorer
-
Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model
A fine-tuned vision-language model with one in-context example classifies product defects with 0.804 MCC on MVTec AD without per-product retraining, though the evaluation protocol needs scrutiny.