A training-free method fits PCA to DINOv2 features from few normal images and detects anomalies via reconstruction residual, reaching SOTA one-shot AUROC of 97.1% image-level on MVTec-AD and 93.2% on VisA.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
Unsupervised anomaly detection with pre-trained Anomalib models achieves F1 macro score over 0.95 on Raspberry Pi using 10 images and 90 seconds training time.
citing papers explorer
-
SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
A training-free method fits PCA to DINOv2 features from few normal images and detects anomalies via reconstruction residual, reaching SOTA one-shot AUROC of 97.1% image-level on MVTec-AD and 93.2% on VisA.
-
Leveraging Unsupervised Learning for Cost-Effective Visual Anomaly Detection
Unsupervised anomaly detection with pre-trained Anomalib models achieves F1 macro score over 0.95 on Raspberry Pi using 10 images and 90 seconds training time.