Triple Generative Adversarial Networks

  title={Triple Generative Adversarial Networks},
  author={Chongxuan Li and Kun Xu and Jiashuo Liu and Jun Zhu and Bo Zhang},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • Chongxuan LiKun Xu Bo Zhang
  • Published 20 December 2019
  • Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN). The generator and the classifier characterize the conditional distributions between images and labels to perform conditional generation and classification, respectively… 

Figures and Tables from this paper

A Review on Generative Adversarial Networks

  • Yiqin YuanYuhao Guo
  • Computer Science
    2020 5th International Conference on Information Science, Computer Technology and Transportation (ISCTT)
  • 2020
The performance of each model on the datasets of MNIST, SVHN, CIFAR10, etc., is evaluated and some of the applications and the methods of optimizing the models of GAN are explained.

ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning

This work considers semi-supervised continual learning (SSCL) that incrementally learns from partially labeled data, and proposes deep Online Replay with Discriminator Consistency (ORDisCo) to interdependently learn a classifier with a conditional generative adversarial network (GAN), which continually passes the learned data distribution to the classifier.

MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis

This work proposes a 3D-aware multi-modal guided hand generative network (MM-Hand), together with a novel geometry-based curriculum learning strategy that can consistently improve the quantitative performance of the state-of-the-art 3D hand pose estimators on two benchmark datasets.

MM-Hand: 3D-Aware Multi-Modal Guided Hand Generation for 3D Hand Pose Synthesis

This work proposes a 3D-aware multi-modal guided hand generative network (MM-Hand), together with a novel geometry-based curriculum learning strategy that can consistently improve the quantitative performance of the state-of-the-art 3D hand pose estimators on two benchmark datasets.

Provable Unrestricted Adversarial Training without Compromise with Generalizability

A novel AT approach called Provable Unrestricted Adversarial Training (PUAT), which can provide a target classifier with comprehensive adversarial robustness against both UAE and RAE, and simultaneously improve its standard generalizability.

Global Nash Equilibrium in Non-convex Multi-player Game: Theory and Algorithms

This paper takes conjugate transformation to the formulation of non-convex multi-player games, and casts the complementary problem into a variational inequality (VI) problem with a continuous pseudo-gradient mapping, and proves the existence condition of global NE.

AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images

The extensive experiments show that the proposed AdvMIL framework could not only bring performance improvement to mainstream WSI models at a relatively low computational cost, but also enable these models to learn from unlabeled data with semi-supervised learning.

VCL-PL:Semi-Supervised Learning from Noisy Web Data with Variational Contrastive Learning

This work uses 40 Gaussian sampling heads for the 40 attributes in the CelebA dataset and applies supervised contrastive learning over a limited amount of labelled data, to address the multi-label face attribute classification problem.

Localizing Microseismic Events Using Semi-Supervised Generative Adversarial Networks

The performance of the microseismic monitoring technique depends greatly on the accuracy of microseismic event localization. Recently, machine learning (ML) methods have been extensively implemented

Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models

Regularized deep generative model (Reg-DGM), which leverages a nontransferable pre-trained model to reduce the variance of generative modeling with limited data, consistently improves the generation performance of strong DGMs including StyleGAN2 and ADA on several benchmarks withlimited data and achieves competitive results to the state-of-the-art methods.



Triple Generative Adversarial Nets

Triple-GAN as a unified model can simultaneously achieve the state-of-the-art classification results among deep generative models, and disentangle the classes and styles of the input and transfer smoothly in the data space via interpolation in the latent space class-conditionally.

Triangle Generative Adversarial Networks

A Triangle Generative Adversarial Network ($\Delta$-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and

Semi-Supervised Learning with Generative Adversarial Networks

This work extends Generative Adversarial Networks to the semi-supervised context by forcing the discriminator network to output class labels and shows that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.

Improved Techniques for Training GANs

This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.

Data Augmentation Generative Adversarial Networks

It is shown that a Data Augmentation Generative Adversarial Network (DAGAN) augments standard vanilla classifiers well and can enhance few-shot learning systems such as Matching Networks.

A Style-Based Generator Architecture for Generative Adversarial Networks

An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.

Large Scale Adversarial Representation Learning

This work builds upon the state-of-the-art BigGAN model, extending it to representation learning by adding an encoder and modifying the discriminator, and demonstrates that these generation-based models achieve the state of the art in unsupervised representation learning on ImageNet, as well as in unconditional image generation.

Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

In this paper we present a method for learning a discriminative classifier from unlabeled or partially labeled data. Our approach is based on an objective function that trades-off mutual information

Training Generative Adversarial Networks with Limited Data

It is demonstrated, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images, and is expected to open up new application domains for GANs.

Training generative neural networks via Maximum Mean Discrepancy optimization

This work considers training a deep neural network to generate samples from an unknown distribution given i.i.d. data to frame learning as an optimization minimizing a two-sample test statistic, and proves bounds on the generalization error incurred by optimizing the empirical MMD.