Triple Generative Adversarial Nets
arXiv:1703.02291
Abstract
Generative Adversarial Nets (GANs) have shown promise in image generation and semi-supervised learning (SSL). However, existing GANs in SSL have two problems: (1) the generator and the discriminator (i.e. the classifier) may not be optimal at the same time; and (2) the generator cannot control the semantics of the generated samples. The problems essentially arise from the two-player formulation, where a single discriminator shares incompatible roles of identifying fake samples and predicting labels and it only estimates the data without considering the labels. To address the problems, we present triple generative adversarial net (Triple-GAN), which consists of three players---a generator, a discriminator and a classifier. The generator and the classifier characterize the conditional distributions between images and labels, and the discriminator solely focuses on identifying fake image-label pairs. We design compatible utilities to ensure that the distributions characterized by the classifier and the generator both converge to the data distribution. Our results on various datasets demonstrate that Triple-GAN as a unified model can simultaneously (1) achieve the state-of-the-art classification results among deep generative models, and (2) disentangle the classes and styles of the input and transfer smoothly in the data space via interpolation in the latent space class-conditionally.
References in corpus (4)
Cited by in corpus (73)
- Recent advances and clinical applications of deep learning in medical image analysis
- Self-supervised Learning: Generative or Contrastive
- Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks
- How Generative Adversarial Networks and Their Variants Work: An Overview
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- Good Semi-supervised Learning that Requires a Bad GAN
- Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
- A Bayesian Data Augmentation Approach for Learning Deep Models
- BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
- Triangle Generative Adversarial Networks
- Small Sample Learning in Big Data Era
- Unsupervised Histopathology Image Synthesis
- PSIGAN: Joint probabilistic segmentation and image distribution matching for unpaired cross-modality adaptation based MRI segmentation
- Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
- Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach
- Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
- Adversarial Symmetric Variational Autoencoder
- Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives
- Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network
- Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
- Structured Generative Adversarial Networks
- High-resolution Deep Convolutional Generative Adversarial Networks
- JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
- Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification
- Fast Compressive Sensing Recovery Using Generative Models with Structured Latent Variables
- Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks
- Hierarchical Adversarially Learned Inference
- VIGAN: Missing View Imputation with Generative Adversarial Networks
- When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets
- Facial UV Map Completion for Pose-invariant Face Recognition: A Novel Adversarial Approach based on Coupled Attention Residual UNets
- Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
- The Six Fronts of the Generative Adversarial Networks
- Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Sentiment Analysis
- Projection Based Weight Normalization for Deep Neural Networks
- More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
- cGANs with Multi-Hinge Loss
- Controllable Generative Adversarial Network
- EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
- Contrastively Smoothed Class Alignment for Unsupervised Domain Adaptation
- Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
- Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training
- Understanding and Stabilizing GANs' Training Dynamics with Control Theory
- Adversarial Learning of General Transformations for Data Augmentation
- How Does GAN-based Semi-supervised Learning Work?
- Multi-objects Generation with Amortized Structural Regularization
- Deep Low-Density Separation for Semi-Supervised Classification
- Manifold Adversarial Learning
- Deep Structured Generative Models
- Generative Adversarial Classifier for Handwriting Characters Super-Resolution
- Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion
- Red-GAN: Attacking class imbalance via conditioned generation. Yet another perspective on medical image synthesis for skin lesion dermoscopy and brain tumor MRI
- Joint Learning of Generative Translator and Classifier for Visually Similar Classes
- Semi-supervised Learning using Adversarial Training with Good and Bad Samples
- Semi-supervised Learning for Few-shot Image-to-Image Translation
- Bi-level Score Matching for Learning Energy-based Latent Variable Models
- Semi-supervised Learning by Latent Space Energy-Based Model of Symbol-Vector Coupling
- Segmentation Guided Image-to-Image Translation with Adversarial Networks
- Semi-supervised Semantic Segmentation of Prostate and Organs-at-Risk on 3D Pelvic CT Images
- Symbiotic Adversarial Learning for Attribute-based Person Search
- Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning
- Adversarially Learned Mixture Model
- Facial Emotion Recognition with Noisy Multi-task Annotations
- Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
- Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
- Domain Partitioning Network
- Exponential Convergence of Gradient Methods in Concave Network Zero-sum Games
- Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy
- Generative Modeling for Multi-task Visual Learning
- Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
- Semi-supervised Learning with Contrastive Predicative Coding
- A Self-Training Method for Semi-Supervised GANs
- Dual-discriminator GAN: A GAN way of profile face recognition
- Regularization with Latent Space Virtual Adversarial Training