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 IEEE/CVF international conference on computer vision , pages=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
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.
- LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention