LOGAN: Latent Optimisation for Generative Adversarial Networks

ICLR 2020 Yan WuJeff DonahueDavid BalduzziKaren SimonyanTimothy Lillicrap

Training generative adversarial networks requires balancing of delicate adversarial dynamics. Even with careful tuning, training may diverge or end up in a bad equilibrium with dropped modes... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Conditional Image Generation ImageNet 128x128 LOGAN (NGD) FID 3.36 # 1
Inception score 148.2 # 1

Methods used in the Paper