Adversarially Learned Inference
Vincent Dumoulin, Mohamed Ishmael Belghazi, Ben Poole et al. · arXiv (Cornell University) · 2016
We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation network maps samples from stochastic latent variables to the data space while the inference network maps training examples in data space to the space of latent variables. An adversarial game is cast between these two networks and a discriminative network is trained to distinguish between joint latent/data-space samples from the generative network and joint samples from the inference network. We illustrate the ability of the model to learn mutually coherent inference and generation networks through the inspections of model samples and reconstructions and confirm the usefulness of the learned representations by obtaining a performance competitive with state-of-the-art on the semi-supervised SVHN and CIFAR10 tasks.
Cited by 579 works. doi:10.48550/arxiv.1606.00704 Open-access PDF
Authors
- Vincent Dumoulin
- Mohamed Ishmael Belghazi
- Ben Poole
- Olivier Mastropietro
- Alex Lamb
- Martín Arjovsky
- Aaron C. Courville
References
- Adam: A Method for Stochastic Optimization
- ImageNet Large Scale Visual Recognition Challenge
- Statistical Learning Theory
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- GAN(Generative Adversarial Nets)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Reading digits in natural images with unsupervised feature learning
- Theano: new features and speed improvements
- Deep Learning Face Attributes in the Wild