Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
Emerging properties in self-supervised vision transformers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
ACCEPT 2representative citing papers
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.
citing papers explorer
-
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wind turbine data with 80% fewer parameters.
-
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.