High Diversity Attribute Guided Face Generation with GANs
arXiv:1806.10982
Abstract
In this work we focused on GAN-based solution for the attribute guided face synthesis. Previous works exploited GANs for generation of photo-realistic face images and did not pay attention to the question of diversity of the resulting images. The proposed solution in its turn introducing novel latent space of unit complex numbers is able to provide the diversity on the "birthday paradox" score 3 times higher than the size of the training dataset. It is important to emphasize that our result is shown on relatively small dataset (20k samples vs 200k) while preserving photo-realistic properties of generated faces on significantly higher resolution (128x128 in comparison to 32x32 of previous works).
References in corpus (29)
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Improved Training of Wasserstein GANs
- Focal Loss for Dense Object Detection
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Adversarially Learned Inference
- Invertible Conditional GANs for image editing
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
- VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- Semantic Segmentation using Adversarial Networks
- Unrolled Generative Adversarial Networks
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Learning Deep Embeddings with Histogram Loss
- Amortised MAP Inference for Image Super-resolution
- Image Super-Resolution Using Deep Convolutional Networks
- Do GANs actually learn the distribution? An empirical study
- Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
- Age Progression/Regression by Conditional Adversarial Autoencoder
- Unsupervised Image-to-Image Translation with Generative Adversarial Networks
- Stacked Generative Adversarial Networks
- Recent Progress of Face Image Synthesis
- Controllable Generative Adversarial Network
- Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
- Variance Regularizing Adversarial Learning
- Contractive De-noising Auto-encoder