Improved Techniques for Training GANs Improved Techniques for Training GANs
Paper summary The Authors provide a bag of tricks for training GAN's in the image domain. Using these, they achieve very strong semi-supervised results on SHVN, MNIST, and CIFAR. The authors then train the improved model on several images datasets, evaluate it on different tasks: semi-supervised learning, and generative capabilities, and achieve state-of-the-art results. This paper investigates several techniques to stabilize GAN training and encourage convergence. Although lack of theoretical justification, the proposed heuristic techniques give better-looking samples. In addition to human judgement, the paper proposes a new metric called Inception score by applying pre-trained deep classification network on the generated samples. By introducing free labels with the generated samples as new category, the paper proposes the experiment using GAN under semi-supervised learning setting, which achieve SOTA semi-supervised performance on several benchmark datasets (MNIST, CIFAR-10, and SVHN).

Loading...
Your comment:
Loading...
I love the format of this summary. Thanks! The historical averaging idea is interesting. This is basically just a momentum update rule right?

that's what I understood (dont have first hand experience)

In minibatch discrimination, we have these $M$ matrices by multiplying with the $T$ tensor. What is the $T$ tensor? In the code it looks like you initialise it like a weight matrix, which means you learn it?

Your comment:
Loading...
Your comment:
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About