A ceramics studio’s research bench has one network inventing extra kiln-defect pictures and a second network trying to spot which pictures are fabricated. Which generative approach is that?
Select an answer to reveal the explanation.
Short Explanation
One network inventing extra kiln-defect pictures and a second trying to spot the fakes is a generative adversarial pair. That contest is how a GAN synthesizes realistic data. A diffusion stack has no second network, and a classifier that only sorts existing photos is not synthesizing anything.
Full Explanation
A GAN is two networks in competition: one synthesizes candidates and the other tries to detect fakes. A diffusion stack, a single classifier, and a coded expert system are different technologies.