Apparaît dans la collection : Statistical Modeling for Shapes and Imaging

State of the art deep generative networks are capable of producing images with such incredible 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 demonstrate this is not sufficient and motivates the need to study memorization/overfitting of deep generators with more scrutiny. This work addresses this question by i) showing how simple losses are highly effective at reconstructing images for deep generators ii) analyzing the statistics of reconstruction errors when reconstructing training and validation images, which is the standard way to analyze overfitting in machine learning. Using this methodology, we show that overfitting is not detectable in the pure GAN models proposed in the literature, in contrast with those using hybrid adversarial losses, which are amongst the most widely applied generative methods. We also show that standard GAN evaluation metrics fail to capture memorization for some deep generators. Finally, experiment shows how off-the-shelf GAN generators can be successfully applied to face inpainting and face super-resolution using the proposed reconstruction method, without hybrid adversarial losses.

(Joint work with Ryan Webster, Loic Simon, Frederic Jurie).