AAND is a two-stage anomaly detection method that advances a pre-trained teacher via residual anomaly amplification and applies hard knowledge distillation in reverse distillation to achieve SOTA results on MVTecAD, VisA, and MVTec3D-RGB.
Describing textures in the wild
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
A non-linear transformation of cosine similarities in localized conformal prediction for VLMs yields statistically significant reductions in mean set sizes while conserving marginal coverage guarantees.
citing papers explorer
-
Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection
AAND is a two-stage anomaly detection method that advances a pre-trained teacher via residual anomaly amplification and applies hard knowledge distillation in reverse distillation to achieve SOTA results on MVTecAD, VisA, and MVTec3D-RGB.
-
Localized Conformal Prediction for Image Classification with Vision-Language Models
A non-linear transformation of cosine similarities in localized conformal prediction for VLMs yields statistically significant reductions in mean set sizes while conserving marginal coverage guarantees.