Self-conditioned Generative Adversarial Networks for Image Editing
Event Type
Technical Paper
Interest Areas
Research & Education
Presentation Types
In Person
Registration Categories
Full Conference Supporter
Full Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
This session WILL NOT be recorded.
TimeTuesday, 9 August 20229:36am - 9:41am PDT
LocationEast Building, Ballroom A/B
DescriptionGANs are susceptible to generative bias. They focus on the core of the distribution, leaving the edges behind. We argue that this bias is responsible for the collapse of latent-editing methods away from the distribution's core and propose a method for self-conditioning the GAN — improving treatment of rare modalities.