Learning on multiple images

[GlebSBrykin]

Is it possible to train a neural network on a group of similar images rather than on a single image?

[cristyioan2000]

The main idea of the paper is training on a single image, for multiple similar images i would sugest: CycleGAN

[JonathanFly]

There's a big gap between typical CycleGAN datasets and a dataset of 1, so adapting this architecture to cover some of the ground in between would still be super cool!

[GlebSBrykin]

CycleGAN can't generate random samples.

[jayzhan211]

There's a big gap between typical CycleGAN datasets and a dataset of 1, so adapting this architecture to cover some of the ground in between would still be super cool!

you mean zebra to horse by single image?