Hierarchical Adversarially Learned Inference

Abstract

We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model. Both the generative and inference model are trained using the adversarial learning paradigm. We demonstrate that the hierarchical structure supports the learning of progressively more abstract representations as well as providing semantically meaningful reconstructions with different levels of fidelity. Furthermore, we show that minimizing the Jensen-Shanon divergence between the generative and inference network is enough to minimize the reconstruction error. The resulting semantically meaningful hierarchical latent structure discovery is exemplified on the CelebA dataset. There, we show that the features learned by our model in an unsupervised way outperform the best handcrafted features. Furthermore, the extracted features remain competitive when compared to several recent deep supervised approaches on an attribute prediction task on CelebA. Finally, we leverage the model's inference network to achieve state-of-the-art performance on a semi-supervised variant of the MNIST digit classification task.

arXiv comment18 pages, 7 figures

References in corpus (13)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• Conditional Image Generation with PixelCNN Decoders
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Pixel Recurrent Neural Networks
• Adversarial Feature Learning
• Adversarially Learned Inference
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Auxiliary Deep Generative Models
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Triple Generative Adversarial Nets
• Discriminative Regularization for Generative Models
• Adversarial Message Passing For Graphical Models

Cited by in corpus (10)

• Fashion-Gen: The Generative Fashion Dataset and Challenge
• Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
• Learning about an exponential amount of conditional distributions
• A Survey of Deep Facial Attribute Analysis
• Evidence Transfer for Improving Clustering Tasks Using External Categorical Evidence
• Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
• Learning to infer in recurrent biological networks
• Stein Latent Optimization for Generative Adversarial Networks
• Learning Improved Representations by Transferring Incomplete Evidence Across Heterogeneous Tasks
• Adversarial Code Learning for Image Generation