Adversarial Training

Singular Value Clipping

Introduced by Saito et al. in Temporal Generative Adversarial Nets with Singular Value Clipping

Singular Value Clipping (SVC) is an adversarial training technique used by TGAN to enforce the 1-Lipschitz constraint of the WGAN objective. It is a constraint to all linear layers in the discriminator that satisfies the spectral norm of weight parameter $W$ is equal or less than one. This means that the singular values of weight matrix are all one or less. Therefore singular value decomposition (SVD) is performed after a parameter update, replacing all the singular values larger than one with one, and the parameters are reconstructed with them. The same operation is applied to convolutional layers by interpreting a higher order tensor in weight parameter as a matrix $\hat{W}$.

Source: Temporal Generative Adversarial Nets with Singular Value Clipping

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Generation 1 50.00%
Video Generation 1 50.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories