Flow-GAN: Bridging implicit and prescribed learning in generative models

By Aditya Grover, Manik Dhar, Stefano Ermon. 2017

24 citations recorded by the source corpus.

Evaluating the performance of generative models for unsupervised learning is inherently challenging due to the lack of well-defined and tractable objectives. This is particularly difficult for implicit models such as generative adversarial networks (GANs) which perform extremely well in practice for tasks such as sample generation, but sidestep the explicit characterization of a density. We propose Flow-GANs, a generative adversarial network with the generator specified as a normalizing flow model which can perform exact likelihood evaluation. Subsequently, we learn a Flow-GAN using a hybrid objective that integrates adversarial training with maximum likelihood estimation. We show empirically the benefits of Flow-GANs on MNIST and CIFAR-10 datasets in learning generative models that can attain low generalization error based on the log-likelihoods and generate high quality samples. Finally, we show a simple, yet hard to beat baseline for GANs based on Gaussian Mixture Models.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Is Generator Conditioning Causally Related to GAN Performance? (2018, methodology): “Invertible Density Estimators and Adversarial Training: In Grover et al. (2017) and Danihelka et al. (2017), adversarial training is compared to maximum likelihood training of generative image models using an invertible decoder as in Dinh et al. (2014; 2016).”
Analyzing Inverse Problems with Invertible Neural Networks (2018, methodology): “Despite their simple design and training, these networks were rarely studied: [5, 15] showed that minimization of an adversarial loss is superior to maximum likelihood training in RealNVPs, [13] used a NICE-like design as a memory-efficient alternative to residual networks, [19] demonstrated that th”
Understanding the (un)interpretability of natural image distributions using generative models (2019, methodology): “Real NVP can be trained using either maximum likelihood methods or adversarial methods, or a combination of both, as in FlowGAN [12].”
Continuous-Time Flows for Efficient Inference and Density Estimation (2017, methodology): “GAN has recently been augmented by Flow-GAN (Grover et al., 2017) to incorporate a likelihood term for explicit density estimation .”
On the Discrimination-Generalization Tradeoff in GANs (2017, methodology): “The FlowGAN (Grover et al., 2017) proposed to combine the WGAN loss and the log likelihood to solve the inconsistency problem.”
r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting (2018, unknown): “Generative models have surged in popularity [9,13,14,16,25,44,51].”
An Introduction to Variational Autoencoders (2019, background): “VAEs and GANs seem to have complementary properties: while GANs can generate images of high subjective perceptual quality, they tend to lack full support over the data [Grover et al., 2017], as opposed to likelihood-based generative models.”