Few-Shot Adaptation of Generative Adversarial Networks

Abstract

Generative Adversarial Networks (GANs) have shown remarkable performance in image synthesis tasks, but typically require a large number of training samples to achieve high-quality synthesis. This paper proposes a simple and effective method, Few-Shot GAN (FSGAN), for adapting GANs in few-shot settings (less than 100 images). FSGAN repurposes component analysis techniques and learns to adapt the singular values of the pre-trained weights while freezing the corresponding singular vectors. This provides a highly expressive parameter space for adaptation while constraining changes to the pretrained weights. We validate our method in a challenging few-shot setting of 5-100 images in the target domain. We show that our method has significant visual quality gains compared with existing GAN adaptation methods. We report qualitative and quantitative results showing the effectiveness of our method. We additionally highlight a problem for few-shot synthesis in the standard quantitative metric used by data-efficient image synthesis works. Code and additional results are available at http://e-271.github.io/few-shot-gan.

References in corpus (15)

• Auto-Encoding Variational Bayes
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Self-Attention Generative Adversarial Networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Learning multiple visual domains with residual adapters
• A mathematical theory of semantic development in deep neural networks
• The Singular Values of Convolutional Layers
• Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs
• Improved generator objectives for GANs
• Transferring GANs: generating images from limited data
• Entanglement and Tensor Networks for Supervised Image Classification
• Transflow Learning: Repurposing Flow Models Without Retraining
• Effective Data Augmentation with Multi-Domain Learning GANs

Cited by in corpus (5)

• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis
• Few-shot Image Generation via Masked Discrimination
• One-Shot Generative Domain Adaptation
• Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
• LATENTPATCH: A Non-Parametric Approach for Face Generation and Editing