paper-with-me

Papers

Improved Techniques for Training Single-Image GANs

2020-03-25 · Tobias Hinz, Matthew Fisher, Oliver Wang, Stefan Wermter

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.

📄 PDF Abstract BibTeX arXiv:2003.11512

Code (4)

tohinz/ConSinGAN 공식 구현 pytorch
maminio/sample-generating pytorch
ryyAudrey/ConMixSinGAN-master pytorch
septmars/DL pytorch

Tasks

Image Generationsingle-image-generation

Similar Papers 제목 키워드 기반

Learning Foreground-Background Segmentation from Improved Layered GANs

2021-04-01 · Yu Yang, Hakan Bilen, Qiran Zou, Wing Yin Cheung 외

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+1

Improved Techniques for Training GANs

2016-06-10 · NeurIPS 2016 12 · Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung 외

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 Classification

Orthogonal Wasserstein GANs

2019-11-29 · Jan Müller, Reinhard Klein, Michael Weinmann

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)

2018-06-29 · Samuel A. Barnett

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

2020-11-13 · Sung Eun Kim, Hongkyu Yoon, Jonghyun Lee

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