<ul><li>A new approach is proposed for improving the performance of generative adversarial networks (GANs) by identifying and removing harmful training instances.</li><li>The challenge with previous approaches is that they are not easily applicable to GANs due to the indirect effect of training instances on GAN parameters.</li><li>The proposed approach uses the Jacobian of the generator's gradient with respect to the discriminator's parameters to estimate the influence of instances.</li><li>By removing the identified harmful instances, the generative performance of GANs is significantly improved on various evaluation metrics.</li></ul>

Data Cleansing for GANs

Discover more