MPFM models flow matching velocity as a Gaussian mixture prior per normal class plus a mutual information regularizer to improve open-set anomaly detection over unimodal prototypes.
arXiv preprint arXiv:2108.00462 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4verdicts
UNVERDICTED 4representative citing papers
IDEAL learns intrinsic deviation vectors via Normal Variation Eraser and Intrinsic Deviation Encoder to score query deviations for both seen and unseen anomalies in discriminative FSAD.
DPDL learns multiple Gaussian prototypes and a Schrödinger bridge diffusion process to enclose normal samples in a compact discriminative space while using hyperspherical dispersion to identify out-of-distribution anomalies, reporting SOTA results on 9 datasets.
Anomaly Preference Optimization reformulates anomaly image generation as preference learning with implicit alignment from real anomalies and a time-aware capacity allocation module in diffusion models.
citing papers explorer
-
Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
MPFM models flow matching velocity as a Gaussian mixture prior per normal class plus a mutual information regularizer to improve open-set anomaly detection over unimodal prototypes.
-
Beyond Normal References: Discriminative Few-Shot Anomaly Detection
IDEAL learns intrinsic deviation vectors via Normal Variation Eraser and Intrinsic Deviation Encoder to score query deviations for both seen and unseen anomalies in discriminative FSAD.
-
Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection
DPDL learns multiple Gaussian prototypes and a Schrödinger bridge diffusion process to enclose normal samples in a compact discriminative space while using hyperspherical dispersion to identify out-of-distribution anomalies, reporting SOTA results on 9 datasets.
-
Anomaly-Preference Image Generation
Anomaly Preference Optimization reformulates anomaly image generation as preference learning with implicit alignment from real anomalies and a time-aware capacity allocation module in diffusion models.