S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels
arXiv:2010.12622
Abstract
Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process. Conditional GANs (cGANs) provide a mechanism to control the generation process by conditioning the output on a user defined input. Although training GANs requires only unsupervised data, training cGANs requires labelled data which can be very expensive to obtain. We propose a framework for semi-supervised training of cGANs which utilizes sparse labels to learn the conditional mapping, and at the same time leverages a large amount of unsupervised data to learn the unconditional distribution. We demonstrate effectiveness of our method on multiple datasets and different conditional tasks.
References in corpus (14)
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- 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
- Categorical Reparameterization with Gumbel-Softmax
- Self-Attention Generative Adversarial Networks
- Adversarial Feature Learning
- Adversarially Learned Inference
- cGANs with Multi-Hinge Loss
- Hybrid VAE: Improving Deep Generative Models using Partial Observations
- Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators