Generative Discrimination

Minibatch Discrimination

Introduced by Salimans et al. in Improved Techniques for Training GANs

Minibatch Discrimination is a discriminative technique for generative adversarial networks where we discriminate between whole minibatches of samples rather than between individual samples. This is intended to avoid collapse of the generator.

Source: Improved Techniques for Training GANs


Paper Code Results Date Stars


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