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.
How to exploit hyperspherical embeddings for out-of-distribution detection? arXiv preprint arXiv:2203.04450, 2022 b
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and ImageNet-1K.
TINS improves OOD detection by learning negative semantics at test time with ID-prototype separation, cutting average FPR95 from 14.04% to 6.72% on the Four-OOD benchmark with ImageNet-1K.
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.
-
ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
ConjNorm reframes OOD detection score design as optimizing norm p in an exponential family density model via a Bregman divergence theorem, with a tractable Monte Carlo estimator, claiming SOTA gains on CIFAR-100 and ImageNet-1K.
-
TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection
TINS improves OOD detection by learning negative semantics at test time with ID-prototype separation, cutting average FPR95 from 14.04% to 6.72% on the Four-OOD benchmark with ImageNet-1K.