Generative Adversarial Networks

Abstract

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.

Cited by in corpus (25)

• Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
• Mixed supervision for surface-defect detection: from weakly to fully supervised learning
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification
• Machine learning-assisted design of material properties
• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
• Face Deidentification with Generative Deep Neural Networks
• Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
• Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks
• Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey
• Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation
• Multichannel Synthetic Preictal EEG Signals to Enhance the Prediction of Epileptic Seizures
• Using Deep Learning to Localize Gravitational Wave Sources
• An ordinal CNN approach for the assessment of neurological damage in Parkinson's disease patients
• A Study of the Generalizability of Self-Supervised Representations
• Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images
• An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis
• Generation of ice states through deep reinforcement learning
• Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
• Fast and computationally efficient generative adversarial network algorithm for unmanned aerial vehicle-based network coverage optimization
• Physics Validation of Novel Convolutional 2D Architectures for Speeding Up High Energy Physics Simulations
• 3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images
• The future of urban models in the Big Data and AI era: a bibliometric analysis (2000-2019)
• Predicting Real-time Scientific Experiments Using Transformer models and Reinforcement Learning
• Efficient Modelling Across Time of Human Actions and Interactions