Description
RealNVP is a generative model that utilises real-valued non-volume preserving (real NVP) transformations for density estimation. The model can perform efficient and exact inference, sampling and log-density estimation of data points.
Papers Using This Method
Time-Causal VAE: Robust Financial Time Series Generator2024-11-05An Investigation into the Performances of the State-of-the-art Machine Learning Approaches for Various Cyber-attack Detection: A Survey2024-02-26APALU: A Trainable, Adaptive Activation Function for Deep Learning Networks2024-02-13On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows2024-02-09Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study2023-11-05Semi-supervised Invertible Neural Operators for Bayesian Inverse Problems2022-09-06Scaling Up Machine Learning For Quantum Field Theory with Equivariant Continuous Flows2021-10-06General Invertible Transformations for Flow-based Generative Modeling2021-06-02Generative Time-series Modeling with Fourier Flows2021-01-01Computer Vision and Normalizing Flow-Based Defect Detection2020-12-12General Invertible Transformations for Flow-based Generative Modeling2020-11-30Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows2020-08-28Gaussianization Flows2020-03-04Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)2020-01-14Adversarial Robustness of Flow-Based Generative Models2019-11-20Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data2019-11-12Tails of Lipschitz Triangular Flows2019-07-10Discrete Flows: Invertible Generative Models of Discrete Data2019-05-24Density estimation using Real NVP2016-05-27