AI engineering glossary · Generative media multimodal
What is cycleGAN?
CycleGAN: A GAN framework for image translation between two domains without paired examples. Two generators translate in opposite directions, and a cycle-consistency loss requires that translating there and back returns the original image.
CycleGAN: an example
Photos of horses are turned into zebras, and translating back recovers the horse, without any matched horse-zebra pairs.
Related terms
More Generative media multimodal terms
- Deepfake
- Denoising diffusion implicit model
- Denoising diffusion probabilistic model
- Denoising strength
- Diffusion model
- Diffusion sampler
- Diffusion transformer
- Discriminator
Where you learn it
CycleGAN is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.