A vector-quantized autoencoder that dynamically allocates code resolution per image patch and uses learned normal budget priors to detect visual defects.
A generic deep-learning-based approach for automated surface inspection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Patch-aware Vector Quantized Codebook Learning for Unsupervised Visual Defect Detection
A vector-quantized autoencoder that dynamically allocates code resolution per image patch and uses learned normal budget priors to detect visual defects.