Whitening and Coloring transform for GANs

12 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Style-Based Generator Architecture for Generative Adversarial Networks (2018, background): “Compared to more general feature transforms [35, 53], AdaIN is particularly well suited for our purposes due to its efficiency and compact representation.”
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning (2021, methodology): “Inspired by [38], it has been used recently in self-supervised learning as a mechanism for preventing the dimensions of the representations from encoding the same information.”
Normalization Techniques in Training DNNs: Methodology, Analysis and Application (2020, methodology): “[79] used Cholesky decomposition (CD) based whitening Σ where L is a lower triangular matrix from the CD, with LL T = Σ .”
Animating Arbitrary Objects via Deep Motion Transfer (2018, methodology): “Several methods derived from Generative Adversarial Networks (GAN) [16] and Variational Autoencoders (VAE) [24] have been proposed to generate images and videos [19, 32, 30, 39, 29, 37, 36, 33].”
Whitening for Self-Supervised Representation Learning (2020, methodology): “Speciﬁcally, given a set of samples V = { v i } , corresponding to the current mini-batch of images B = { x i } , we ﬁrst project the elements of V onto a spherical distribution using a whitening transform (Siarohin et al., 2019).”