Improved Techniques for Training Single-Image GANs
Recently there has been an interest in the potential of learning generative models from a single image, as opposed to from a large dataset. This task is of practical significance, as it means that generative models can be used in domains where collecting a large dataset is not feasible. However, training a model capable of generating realistic images from only a single sample is a difficult problem. In this work, we conduct a number of experiments to understand the challenges of training these methods and propose some best practices that we found allowed us to generate improved results over previous work in this space. One key piece is that unlike prior single image generation methods, we concurrently train several stages in a sequential multi-stage manner, allowing us to learn models with fewer stages of increasing image resolution. Compared to a recent state of the art baseline, our model is up to six times faster to train, has fewer parameters, and can better capture the global structure of images.
Code (4)
Tasks
Image Generationsingle-image-generationSimilar Papers 제목 키워드 기반
Learning Foreground-Background Segmentation from Improved Layered GANs
Deep learning approaches heavily rely on high-quality human supervision which is nonetheless expensive, time-consuming, and error-prone, especially for image segmentation task. In this paper, we propose a method to autom…
Generative Adversarial NetworkImage SegmentationSegmentationSemantic Segmentation+1Improved Techniques for Training GANs
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. We focus on two applications of GANs: semi-supervised learning, and the ge…
Conditional Image GenerationImage GenerationSemi-Supervised Image ClassificationOrthogonal Wasserstein GANs
Wasserstein-GANs have been introduced to address the deficiencies of generative adversarial networks (GANs) regarding the problems of vanishing gradients and mode collapse during the training, leading to improved converg…
Convergence Problems with Generative Adversarial Networks (GANs)
Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many te…
Fast and Scalable Earth Texture Synthesis using Spatially Assembled Generative Adversarial Neural Networks
The earth texture with complex morphological geometry and compositions such as shale and carbonate rocks, is typically characterized with sparse field samples because of an expensive and time-consuming characterization p…
Computational EfficiencyTexture Synthesis