NRM enables OoD detection by joint latent likelihood, assigning lower values to SVHN than CIFAR-10 (unlike VAEs/flows) and consistent across other OoD sets.
Efficient GAN-Based Anomaly Detection
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Generative adversarial networks (GANs) are able to model the complex highdimensional distributions of real-world data, which suggests they could be effective for anomaly detection. However, few works have explored the use of GANs for the anomaly detection task. We leverage recently developed GAN models for anomaly detection, and achieve state-of-the-art performance on image and network intrusion datasets, while being several hundred-fold faster at test time than the only published GAN-based method.
verdicts
UNVERDICTED 3representative citing papers
Supervised ClassMix and a Sup-Unsup Feature Discriminator yield an average 2.07% mIoU gain over standard semi-supervised methods on Chase and COVID-19 datasets.
SMT-AD detects anomalies via superposed multiresolution bond-dimension-1 MPOs with Fourier embedding, claiming competitive baseline performance and linear parameter scaling.
citing papers explorer
-
Out-of-Distribution Detection Using Neural Rendering Generative Models
NRM enables OoD detection by joint latent likelihood, assigning lower values to SVHN than CIFAR-10 (unlike VAEs/flows) and consistent across other OoD sets.
-
Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator
Supervised ClassMix and a Sup-Unsup Feature Discriminator yield an average 2.07% mIoU gain over standard semi-supervised methods on Chase and COVID-19 datasets.
-
SMT-AD: a scalable quantum-inspired anomaly detection approach
SMT-AD detects anomalies via superposed multiresolution bond-dimension-1 MPOs with Fourier embedding, claiming competitive baseline performance and linear parameter scaling.