Instance Selection for GANs

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... (read more)

PDF Abstract NeurIPS 2020 PDF NeurIPS 2020 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Conditional Image Generation ImageNet 128x128 BigGAN + instance selection FID 9.61 # 6
Inception score 114.32 # 3

Methods used in the Paper