A few-shot embedding guides a frozen latent diffusion model to generate realistic industrial defects inside bounding boxes, and a weakly supervised loss improves DRAEM and DeSTSeg on MVTec, pending clarification of test-set overlap.
In: NeurIPSW (2019)
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
-
Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
A few-shot embedding guides a frozen latent diffusion model to generate realistic industrial defects inside bounding boxes, and a weakly supervised loss improves DRAEM and DeSTSeg on MVTec, pending clarification of test-set overlap.