← Search

Loic Simon

2 accepted papers

2019

Detecting Overfitting of Deep Generative Networks via Latent Recovery

CVPR 2019poster

State of the art deep generative networks have achieved such realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest neighbors, to suggest generated images are not simply memorized. We argue this is not sufficie…

Cited by 126PDFScholar