Under cold-start scarcity, ArcAD's Sinkhorn-balanced hyperspherical clustering plus anomaly-guided repulsion lifts reconstruction-based anomaly detection, with the clearest gains (+3.7 to +11.2 I-AUROC) on large multi-class benchmarks.
Learning with mixture of prototypes for out-of-distribution detection
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
EIHF injects high-frequency evidence early to reshape class-conditional feature geometry and reduce ID/OOD Mahalanobis overlap for geometry-sensitive OOD detection.
Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.
MM++ fuses entropy-selected intermediate layers with terminal features via Ledoit-Wolf regularized covariance for scale-invariant unsupervised OOD detection across architectures.
citing papers explorer
-
ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection
Under cold-start scarcity, ArcAD's Sinkhorn-balanced hyperspherical clustering plus anomaly-guided repulsion lifts reconstruction-based anomaly detection, with the clearest gains (+3.7 to +11.2 I-AUROC) on large multi-class benchmarks.
-
Early High-Frequency Injection for Geometry-Sensitive OOD Detection
EIHF injects high-frequency evidence early to reshape class-conditional feature geometry and reduce ID/OOD Mahalanobis overlap for geometry-sensitive OOD detection.
-
Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.
-
MM++: Unsupervised Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion
MM++ fuses entropy-selected intermediate layers with terminal features via Ledoit-Wolf regularized covariance for scale-invariant unsupervised OOD detection across architectures.