AMI-Net adaptively masks anomalous regions in pretrained feature maps, inpaints them with a transformer, and uses reconstruction error for real-time industrial anomaly detection and localization.
Reconstruction by inpainting for visual anomaly detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localization
AMI-Net adaptively masks anomalous regions in pretrained feature maps, inpaints them with a transformer, and uses reconstruction error for real-time industrial anomaly detection and localization.