Discriminator
View article
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium Open
Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible. However, the convergence of GAN training has still not been proved. We propose a two time-scale updat…
View article
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient Open
As a new way of training generative models, Generative Adversarial Net (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data. However, it has li…
View article
Self-Attention Generative Adversarial Networks Open
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details a…
View article
Spectral Normalization for Generative Adversarial Networks Open
One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the discr…
View article
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling Open
We study the problem of 3D object generation. We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional …
View article
Progressive Growing of GANs for Improved Quality, Stability, and Variation Open
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details …
View article
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network Open
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super…
View article
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks Open
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant ar…
View article
EANN Open
As news reading on social media becomes more and more popular, fake news becomes a major issue concerning the public and government. The fake news can take advantage of multimedia content to mislead readers and get dissemination, which can…
View article
Training Generative Adversarial Networks with Limited Data Open
Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes train…
View article
Multi-Adversarial Domain Adaptation Open
Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains. Existing domain advers…
View article
Adversarial Learning for Neural Dialogue Generation Open
We apply adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances. We cast the task as a reinforcement learning problem where we joi…
View article
BEGAN: Boundary Equilibrium Generative Adversarial Networks Open
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. A…
View article
Wasserstein Distance Guided Representation Learning for Domain Adaptation Open
Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution. One solution to domain adaptation is to le…
View article
Compressed Sensing MRI Reconstruction Using a Generative Adversarial Network With a Cyclic Loss Open
Compressed sensing magnetic resonance imaging (CS-MRI) has provided theoretical foundations upon which the time-consuming MRI acquisition process can be accelerated. However, it primarily relies on iterative numerical solvers, which still …
View article
Which Training Methods for GANs do actually Converge? Open
Recent work has shown local convergence of GAN training for absolutely continuous data and generator distributions. In this paper, we show that the requirement of absolute continuity is necessary: we describe a simple yet prototypical coun…
View article
The relativistic discriminator: a key element missing from standard GAN Open
In standard generative adversarial network (SGAN), the discriminator estimates the probability that the input data is real. The generator is trained to increase the probability that fake data is real. We argue that it should also simultane…
View article
Semi-Supervised Learning with Generative Adversarial Networks Open
We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N…
View article
Quantum Generative Adversarial Learning Open
Generative adversarial networks represent a powerful tool for classical machine learning: a generator tries to create statistics for data that mimics those of a true data set, while a discriminator tries to discriminate between the true an…
View article
Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network Open
Heart disease is a malignant threat to human health. Electrocardiogram (ECG) tests are used to help diagnose heart disease by recording the heart’s activity. However, automated medical-aided diagnosis with computers usually requires a larg…
View article
GAIN: Missing Data Imputation using Generative Adversarial Nets Open
We propose a novel method for imputing missing data by adapting the well-known Generative Adversarial Nets (GAN) framework. Accordingly, we call our method Generative Adversarial Imputation Nets (GAIN). The generator (G) observes some comp…
View article
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium Open
When it comes to the formation of real-looking images using some complex models, Generative Adversarial Networks do not disappoint. The complex models involved are often the types with infeasible maximum likelihoods. Be that as it may, the…
View article
DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data Open
Despite over two decades of progress, imbalanced data is still considered a significant challenge for contemporary machine learning models. Modern advances in deep learning have further magnified the importance of the imbalanced data probl…
View article
Quantum generative adversarial networks Open
Quantum machine learning is expected to be one of the first potential\ngeneral-purpose applications of near-term quantum devices. A major recent\nbreakthrough in classical machine learning is the notion of generative\nadversarial training,…
View article
Self-Attention Generative Adversarial Networks Open
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details a…
View article
Unrolled Generative Adversarial Networks Open
We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal disc…
View article
Cross-Modality Person Re-Identification with Generative Adversarial Training Open
Person re-identification (Re-ID) is an important task in video surveillance which automatically searches and identifies people across different cameras. Despite the extensive Re-ID progress in RGB cameras, few works have studied the Re-ID …
View article
cGANs with Projection Discriminator Open
We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast w…
View article
LOGAN: Membership Inference Attacks Against Generative Models Open
Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data poin…
View article
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing Open
This paper presents a new pre-trained language model, DeBERTaV3, which improves the original DeBERTa model by replacing mask language modeling (MLM) with replaced token detection (RTD), a more sample-efficient pre-training task. Our analys…