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.
Proceedings of the Computer Vision and Pattern Recognition Conference , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Anomaly Preference Optimization reformulates anomaly image generation as preference learning using real anomalies for implicit alignment signals from denoising trajectories plus a time-aware capacity allocation module.
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.
-
Anomaly-Preference Image Generation
Anomaly Preference Optimization reformulates anomaly image generation as preference learning using real anomalies for implicit alignment signals from denoising trajectories plus a time-aware capacity allocation module.