Vector quantization: Difference between revisions

Revision as of 23:00, 6 May 2020

Revision as of 23:03, 6 May 2020

Line 106:

As VQ is seeking for centroids as density points of nearby lying samples, it can be also directly used as a prototype-based clustering method: each centroid is then associated with one prototype.

By aiming to minimize the expected squared quantization error<ref>{{cite journal|last=Gray|first=R.M.|title=Vector Quantization|journal=IEEE ASSP Magazine|year=1984|volume=1|issue=2|pages=4–29|doi=10.1109/massp.1984.1162229}}</ref> and introducing a decreasing learning gain fulfilling the Robbins-Monro conditions, multiple iterations over the whole data set with a concrete but fixed number of prototypes converges to the solution of [[k-means]] clustering algorithm in an incremental manner.

*=== [Generative Adversarial Networks (GAN)] ===

VQ has been used to quantize the feature in the discriminator of GANs. The feature quantization (FQ) technique perform implicit feature matching. It improves the GAN training, and yield 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 ==

Line 122 ⟶ 125:

* [[Autoencoder]]

* [[Deep Learning]]

* [Generative Adversarial Networks (GAN)]

''Part of this article was originally based on material from the [[Free On-line Dictionary of Computing]] and is used with [[Wikipedia:Foldoc license|permission]] under the GFDL.''