OCGAN

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

Anomaly DetectiononHyper-Kvasir Dataset
AUC· 2019-03-20
0.813
best: 0.972 (CCD)
SOTA
OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations arXiv:1903.08550
Anomaly DetectiononOne-class CIFAR-10
AUROC· 2019-03-20
66.83
best: 99.6 (CLIP (OE))
OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations arXiv:1903.08550