Journal of Japan Society for Fuzzy Theory and Intelligent Informatics· 2017
GAN（Generative Adversarial Nets）
- 21,802citations
- 2017year
Short summary
A novel framework uses an adversarial process to train generative models, where a generator (G) learns the data distribution by trying to fool a discriminator (D) that estimates sample origin.
AI-generated from the title and abstract; the full text is not read.
Key points
- Proposes a framework for generative models using an adversarial process.
- Simultaneously trains a generator (G) and a discriminator (D).
- G learns the data distribution by maximizing D's errors.
- Framework is trainable with backpropagation using multilayer perceptrons.
AI-generated from the title and abstract; the full text is not read.
Abstract
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to ½ everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
The authors' abstract, as published at the source. Journal of Japan Society for Fuzzy Theory and Intelligent Informatics, 2017 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science