Triple Generative Adversarial Networks
arXiv:1912.09784
Abstract
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. The discriminator solely focuses on identifying fake image-label pairs. Under a nonparametric assumption, we prove the unique equilibrium of the game is that the distributions characterized by the generator and the classifier converge to the data distribution. As a byproduct of the three-player mechanism, Triple-GAN is flexible to incorporate different semi-supervised classifiers and GAN architectures. We evaluate Triple-GAN in two challenging settings, namely, semi-supervised learning and the extreme low data regime. In both settings, Triple-GAN can achieve excellent classification results and generate meaningful samples in a specific class simultaneously. In particular, using a commonly adopted 13-layer CNN classifier, Triple-GAN outperforms extensive semi-supervised learning methods substantially on more than 10 benchmarks no matter data augmentation is applied or not.
References in corpus (42)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- mixup: Beyond Empirical Risk Minimization
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Spectral Normalization for Generative Adversarial Networks
- End to End Learning for Self-Driving Cars
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Conditional Image Generation with PixelCNN Decoders
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Temporal Ensembling for Semi-Supervised Learning
- Convolutional Neural Networks for Sentence Classification
- Training Generative Adversarial Networks with Limited Data
- Interpolation Consistency Training for Semi-Supervised Learning
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Adversarial Feature Learning
- Adversarially Learned Inference
- Semi-Supervised Learning with Ladder Networks
- Semi-Supervised Learning with Generative Adversarial Networks
- A note on the evaluation of generative models
- cGANs with Projection Discriminator
- Large Scale Adversarial Representation Learning
- Generative Moment Matching Networks
- Distributional Smoothing with Virtual Adversarial Training
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Shake-Shake regularization
- Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
- Auxiliary Deep Generative Models
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Improved Consistency Regularization for GANs
- Graphical Generative Adversarial Networks
- JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
- Max-margin Deep Generative Models
- DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification