RoBiS, combining Swin-Cropping, augmentation, adaptive thresholding, and SAM refinement, reports SegF1 of 51.00% and 46.52% on MVTec AD 2 private test sets.
Correcting deviations from normality: A reformulated diffusion model for multi-class unsupervised anomaly detection
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
support 1representative citing papers
citing papers explorer
-
RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images
RoBiS, combining Swin-Cropping, augmentation, adaptive thresholding, and SAM refinement, reports SegF1 of 51.00% and 46.52% on MVTec AD 2 private test sets.