Generative Adversarial Network Architectures For Image Synthesis Using Capsule Networks
arXiv:1806.03796
Abstract
In this paper, we propose Generative Adversarial Network (GAN) architectures that use Capsule Networks for image-synthesis. Based on the principal of positional-equivariance of features, Capsule Network's ability to encode spatial relationships between the features of the image helps it become a more powerful critic in comparison to Convolutional Neural Networks (CNNs) used in current architectures for image synthesis. Our proposed GAN architectures learn the data manifold much faster and therefore, synthesize visually accurate images in significantly lesser number of training samples and training epochs in comparison to GANs and its variants that use CNNs. Apart from analyzing the quantitative results corresponding the images generated by different architectures, we also explore the reasons for the lower coverage and diversity explored by the GAN architectures that use CNN critics.
arXiv commentPre-print
References in corpus (9)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Improved Training of Wasserstein GANs
- Improved Techniques for Training GANs
- A Note on the Inception Score
- From Facial Parts Responses to Face Detection: A Deep Learning Approach
- Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs