A physics-inspired synthetic defect generator plus a loss-based sample reweighting scheme reports high pixel-level AUROC on MVTec AD, VisA, and BTAD, while image-level state-of-the-art is not fully supported.
DRÆM: A discriminatively trained reconstruction embedding for surface anomaly detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection
A physics-inspired synthetic defect generator plus a loss-based sample reweighting scheme reports high pixel-level AUROC on MVTec AD, VisA, and BTAD, while image-level state-of-the-art is not fully supported.