Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training

by   Siddarth Asokan, et al.

Training Generative adversarial networks (GANs) stably is a challenging task. The generator in GANs transform noise vectors, typically Gaussian distributed, into realistic data such as images. In this paper, we propose a novel approach for training GANs with images as inputs, but without enforcing any pairwise constraints. The intuition is that images are more structured than noise, which the generator can leverage to learn a more robust transformation. The process can be made efficient by identifying closely related datasets, or a “friendly neighborhood” of the target distribution, inspiring the moniker, Spider GAN. To define friendly neighborhoods leveraging proximity between datasets, we propose a new measure called the signed inception distance (SID), inspired by the polyharmonic kernel. We show that the Spider GAN formulation results in faster convergence, as the generator can discover correspondence even between seemingly unrelated datasets, for instance, between Tiny-ImageNet and CelebA faces. Further, we demonstrate cascading Spider GAN, where the output distribution from a pre-trained GAN generator is used as the input to the subsequent network. Effectively, transporting one distribution to another in a cascaded fashion until the target is learnt – a new flavor of transfer learning. We demonstrate the efficacy of the Spider approach on DCGAN, conditional GAN, PGGAN, StyleGAN2 and StyleGAN3. The proposed approach achieves state-of-the-art Frechet inception distance (FID) values, with one-fifth of the training iterations, in comparison to their baseline counterparts on high-resolution small datasets such as MetFaces, Ukiyo-E Faces and AFHQ-Cats.


page 25

page 33

page 34

page 35

page 37

page 38

page 40

page 41


GANs Settle Scores!

Generative adversarial networks (GANs) comprise a generator, trained to ...

Instance-Conditioned GAN

Generative Adversarial Networks (GANs) can generate near photo realistic...

Is Generator Conditioning Causally Related to GAN Performance?

Recent work (Pennington et al, 2017) suggests that controlling the entir...

Virtual Conditional Generative Adversarial Networks

When trained on multimodal image datasets, normal Generative Adversarial...

Improving sample diversity of a pre-trained, class-conditional GAN by changing its class embeddings

Mode collapse is a well-known issue with Generative Adversarial Networks...

HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN

In this paper, we present a novel network for high resolution video gene...

Stereotype-Free Classification of Fictitious Faces

Equal Opportunity and Fairness are receiving increasing attention in art...

Please sign up or login with your details

Forgot password? Click here to reset