CLAD, a contrastive vision-language model for industrial anomaly detection, reports higher scores than four baselines on MVTec-AD, but its own Table 1 shows it loses to WinCLIP on VisA pixel-level AUC.
In: Meila, M., Zhang, T
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection
CLAD, a contrastive vision-language model for industrial anomaly detection, reports higher scores than four baselines on MVTec-AD, but its own Table 1 shows it loses to WinCLIP on VisA pixel-level AUC.