Discriminator Feature-based Inference by Recycling the Discriminator of GANs

Abstract

Generative adversarial networks (GANs)successfully generate high quality data by learning amapping from a latent vector to the data. Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for advanced data analysis and manipulation. To analyze the real data in thelatent space of a GAN, it is necessary to build an inference mapping from the data to the latent vector. Thispaper proposes an effective algorithm to accurately infer the latent vector by utilizing GAN discriminator features. Our primary goal is to increase inference mappingaccuracy with minimal training overhead. Furthermore,using the proposed algorithm, we suggest a conditionalimage generation algorithm, namely a spatially conditioned GAN. Extensive evaluations confirmed that theproposed inference algorithm achieved more semantically accurate inference mapping than existing methodsand can be successfully applied to advanced conditionalimage generation tasks.

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Self-Attention Generative Adversarial Networks
• Improved Training of Wasserstein GANs
• Improved Techniques for Training GANs
• One weird trick for parallelizing convolutional neural networks
• Which Training Methods for GANs do actually Converge?
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Adversarial Feature Learning
• Adversarially Learned Inference
• Autoencoding beyond pixels using a learned similarity metric
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Adversarial Autoencoders
• Mode Regularized Generative Adversarial Networks
• Improved Training of Generative Adversarial Networks Using Representative Features

Cited by in corpus (1)

• Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously