中文
相关论文

相关论文: Semi-Supervised Learning with GANs: Revisiting Man…

200 篇论文

Current Generative Adversarial Networks (GANs) produce photorealistic renderings of portrait images. Embedding real images into the latent space of such models enables high-level image editing. While recent methods provide considerable…

图形学 · 计算机科学 2021-09-21 Thomas Leimkühler , George Drettakis

Generative adversarial networks (GANs) have emerged as a powerful tool for generating high-fidelity data. However, the main bottleneck of existing approaches is the lack of supervision on the generator training, which often results in…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Baoren Xiao , Hao Ni , Weixin Yang

We propose a novel training procedure for improving the performance of generative adversarial networks (GANs), especially to bidirectional GANs. First, we enforce that the empirical distribution of the inverse inference network matches the…

机器学习 · 统计学 2020-05-26 Pablo Sánchez-Martín , Pablo M. Olmos , Fernando Perez-Cruz

We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN is trained to maximize the linear separability between…

机器学习 · 统计学 2017-07-26 Zhun Sun , Mete Ozay , Takayuki Okatani

Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process.…

机器学习 · 计算机科学 2020-10-27 Arunava Chakraborty , Rahul Ragesh , Mahir Shah , Nipun Kwatra

Generative Adversarial Networks (GANs) coupled with self-supervised tasks have shown promising results in unconditional and semi-supervised image generation. We propose a self-supervised approach (LT-GAN) to improve the generation quality…

计算机视觉与模式识别 · 计算机科学 2020-10-21 Parth Patel , Nupur Kumari , Mayank Singh , Balaji Krishnamurthy

We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks. Taking an image as input, we first predict building segmentation maps exploiting generic fully convolutional…

计算机视觉与模式识别 · 计算机科学 2020-12-18 Stefano Zorzi , Ksenia Bittner , Friedrich Fraundorfer

With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due…

计算机视觉与模式识别 · 计算机科学 2017-07-21 Ashish Shrivastava , Tomas Pfister , Oncel Tuzel , Josh Susskind , Wenda Wang , Russ Webb

Since their invention, generative adversarial networks (GANs) have become a popular approach for learning to model a distribution of real (unlabeled) data. Convergence problems during training are overcome by Wasserstein GANs which minimize…

机器学习 · 统计学 2018-03-06 Henning Petzka , Asja Fischer , Denis Lukovnicov

Generative Adversarial Networks (GANs), though powerful, is hard to train. Several recent works (brock2016neural,miyato2018spectral) suggest that controlling the spectra of weight matrices in the discriminator can significantly improve the…

机器学习 · 计算机科学 2019-03-05 Haoming Jiang , Zhehui Chen , Minshuo Chen , Feng Liu , Dingding Wang , Tuo Zhao

Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding high-quality images. While high-quality image acquisition is…

图像与视频处理 · 电气工程与系统科学 2021-06-30 Uddeshya Upadhyay , Suyash Awate

One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the training of the…

机器学习 · 计算机科学 2018-02-19 Takeru Miyato , Toshiki Kataoka , Masanori Koyama , Yuichi Yoshida

In this paper, we present the Lipschitz regularization theory and algorithms for a novel Loss-Sensitive Generative Adversarial Network (LS-GAN). Specifically, it trains a loss function to distinguish between real and fake samples by…

计算机视觉与模式识别 · 计算机科学 2019-11-19 Guo-Jun Qi

Generative Adversarial Networks are used for generating the data using a generator and a discriminator, GANs usually produce high-quality images, but training GANs in an adversarial setting is a difficult task. GANs require high computation…

计算机视觉与模式识别 · 计算机科学 2023-08-01 Md Nurul Muttakin , Malik Shahid Sultan , Robert Hoehndorf , Hernando Ombao

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Shuhan Tan , Yujun Shen , Bolei Zhou

To improve the stability of GAN training we need to understand why they can produce realistic samples. Presently, this is attributed to properties of the divergence obtained under an optimal discriminator. This argument has a fundamental…

机器学习 · 计算机科学 2020-11-03 Florian Schäfer , Hongkai Zheng , Anima Anandkumar

In this work, we explore the potential of self-supervised learning with Generative Adversarial Networks (GANs) for electron microscopy datasets. We show how self-supervised pretraining facilitates efficient fine-tuning for a spectrum of…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Bashir Kazimi , Karina Ruzaeva , Stefan Sandfeld

Generative Adversarial Networks (GANs) have been used in several machine learning tasks such as domain transfer, super resolution, and synthetic data generation. State-of-the-art GANs often use tens of millions of parameters, making them…

机器学习 · 计算机科学 2019-02-04 Angeline Aguinaldo , Ping-Yeh Chiang , Alex Gain , Ameya Patil , Kolten Pearson , Soheil Feizi

Generative Adversarial Networks (GANs) is a powerful family of models that learn an underlying distribution to generate synthetic data. Many existing studies of GANs focus on improving the realness of the generated image data for visual…

机器学习 · 计算机科学 2021-11-04 Si-An Chen , Chun-Liang Li , Hsuan-Tien Lin

Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to…

计算机视觉与模式识别 · 计算机科学 2020-08-25 Ning Yu , Ke Li , Peng Zhou , Jitendra Malik , Larry Davis , Mario Fritz