Vector quantization: Difference between revisions

Content deleted Content added
Monkbot (talk | contribs)
m Task 18 (cosmetic): eval 9 templates: del empty params (1×); hyphenate params (2×);
Yobot (talk | contribs)
m Generative Adversarial Networks (GAN): References after punctuation per WP:REFPUNCT, WP:CITEFOOT, WP:PAIC + other fixes
Line 108:
 
=== Generative Adversarial Networks (GAN) ===
VQ has been used to quantize a feature representation layer in the discriminator of GANs. The feature quantization (FQ) technique performs implicit feature matching.<ref>Feature Quantization Improves GAN Training https://arxiv.org/abs/2004.02088</ref>. It improves the GAN training, and yields an improved performance on a variety of popular GAN models: BigGAN for image generation, StyleGAN for face synthesis, and U-GAT-IT for unsupervised image-to-image translation.
 
== See also ==