Transferring GANs: generating images from limited data
Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pretrained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when the target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pretrained model was trained without conditioning. Our results also suggest that density may be more important than diversity and a dataset with one or few densely sampled classes may be a better source model than more diverse datasets such as ImageNet or Places.
Code (1)
Tasks
10-shot image generationDiversityDomain AdaptationImage GenerationSimilar Papers 제목 키워드 기반
Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality training data while producing a small number…
Generative Adversarial NetworkImage GenerationSynthesizing New Retinal Symptom Images by Multiple Generative Models
Age-Related Macular Degeneration (AMD) is an asymptomatic retinal disease which may result in loss of vision. There is limited access to high-quality relevant retinal images and poor understanding of the features definin…
General ClassificationImage GenerationTransferring Unconditional to Conditional GANs with Hyper-Modulation
GANs have matured in recent years and are able to generate high-resolution, realistic images. However, the computational resources and the data required for the training of high-quality GANs are enormous, and the study o…
Conditional Image GenerationContrastive LearningTransfer LearningDetection, Attribution and Localization of GAN Generated Images
Recent advances in Generative Adversarial Networks (GANs) have led to the creation of realistic-looking digital images that pose a major challenge to their detection by humans or computers. GANs are used in a wide range …
AttributeEnhancing Medical Imaging with GANs Synthesizing Realistic Images from Limited Data
In this research, we introduce an innovative method for synthesizing medical images using generative adversarial networks (GANs). Our proposed GANs method demonstrates the capability to produce realistic synthetic images…
Model Optimization