Instance Selection for GANs

By Terrance Devries, Michal Drozdzal, Graham W. Taylor. 2020

41 citations recorded by the source corpus.

Recent advances in Generative Adversarial Networks (GANs) have led to their widespread adoption for the purposes of generating high quality synthetic imagery. While capable of generating photo-realistic images, these models often produce unrealistic samples which fall outside of the data manifold. Several recently proposed techniques attempt to avoid spurious samples, either by rejecting them after generation, or by truncating the model's latent space. While effective, these methods are inefficient, as large portions of model capacity are dedicated towards representing samples that will ultimately go unused. In this work we propose a novel approach to improve sample quality: altering the training dataset via instance selection before model training has taken place. To this end, we embed data points into a perceptual feature space and use a simple density model to remove low density regions from the data manifold. By refining the empirical data distribution before training we redirect model capacity towards high-density regions, which ultimately improves sample fidelity. We evaluate our method by training a Self-Attention GAN on ImageNet at 64x64 resolution, where we outperform the current state-of-the-art models on this task while using 1/2 of the parameters. We also highlight training time savings by training a BigGAN on ImageNet at 128x128 resolution, achieving a 66% increase in Inception Score and a 16% improvement in FID over the baseline model with less than 1/4 the training time.

Subfields: Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Diffusion Models Beat GANs on Image Synthesis (2021, background): “[16] found that filtering out low-density regions of the training set improves GAN training performance.”
GAN-Supervised Dense Visual Alignment (2021, background): “al [18]), both steps together provide the greatest speed-up.”
Instance-Conditioned GAN (2021, background): “density regions, which degrades the quality of the generated samples [11].”
The Role of ImageNet Classes in Fréchet Inception Distance (2022, methodology): “We also suspect that similar interference with FID can happen when the ImageNet pre-trained classifiers are used to curate the training data [9] or as a part of the sampling process [57].”