paper-with-me

Papers

Improved Techniques for Training GANs

2016-06-10 · NeurIPS 2016 12 · Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen

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 generation of images that humans find visually realistic. Unlike most work on generative models, our primary goal is not to train a model that assigns high likelihood to test data, nor do we require the model to be able to learn well without using any labels. Using our new techniques, we achieve state-of-the-art results in semi-supervised classification on MNIST, CIFAR-10 and SVHN. The generated images are of high quality as confirmed by a visual Turing test: our model generates MNIST samples that humans cannot distinguish from real data, and CIFAR-10 samples that yield a human error rate of 21.3%. We also present ImageNet samples with unprecedented resolution and show that our methods enable the model to learn recognizable features of ImageNet classes.

📄 PDF Abstract BibTeX arXiv:1606.03498

Code (46)

openai/improved-gan 공식 구현 tf
openai/improved_gan 공식 구현 tf
BeyondCloud/Comp04_ReverseImageCaption tf
Kyan-Ge/Semi-supervised-Gan pytorch
LsAntonio/60daysofudacity pytorch
MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Improved_Techniques_for_Training_GANs pytorch
MindSpore-scientific-2/code-12/tree/main/GAN-master mindspore
TahmasbiM/Example tf
TomokiKomiya/SRGAN-keras tf
Vishal-V/StackGAN tf
WGLab/SGAN pytorch
ZhimingZhou/AM-GAN tf
aelnouby/Text-to-Image-Synthesis pytorch
agupta231/CARROL tf
andrearama/Deep-Auxiliary-Classifier-GAN pytorch
arnonbruno/ganify tf
chameleonTK/continual-learning-for-HAR pytorch
daixiangzi/ImprovedGan-pytorch pytorch
deepak112/Keras-SRGAN tf
djsinghnegi/SRINImageEnhancemrntGAN tf
fastforwardlabs/deepad tf
fmorenovr/Semi-Supervised-Learning_with_GAN_Keras tf
francis-kang/handson-unsupervised-learning tf
franroldans/tfm-franroldan-wav2pix pytorch
geekysethi/triplet-GAN pytorch
hanzhanggit/StackGAN-inception-model tf
healthcare-robotics/mr-gan
helmy-elrais/Semi_Supervised_Learning pytorch
mlz8/GAN-Reading-List
nanwei1/MNIST_GAN pytorch
nupurkmr9/vision-aided-gan pytorch
raahii/evan pytorch
raahii/video-gans-evaluation pytorch
sanghviyashiitb/GANS-VanillaAndMinibatchDiscrimination pytorch
sbarratt/inception-score-pytorch pytorch
snow-mn/GAN-INT-CLS pytorch
t0nberryking/DCGAN256
tdrussell/IllustrationGAN tf
tensorflow/models/tree/master/research/gan tf
theidentity/Improved-GAN-PyTorch pytorch
tsc2017/Inception-Score tf
victordibia/deepad tf
vuanhtu1993/Keras-SRGANs tf
watsonyanghx/GAN_Lib_Tensorflow tf
wilson1yan/VideoGPT pytorch
zhenxuan00/triple-gan pytorch

Tasks

Conditional Image GenerationImage GenerationSemi-Supervised Image Classification

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
Virtual Batch Normalization Virtual Batch Normalization is a normalization method used for training generative adversarial networks that extends batch normalization. Regular [batch…
GAN Feature Matching Feature Matching is a regularizing objective for a generator in generative adversarial networks
Weight Normalization Weight Normalization is a normalization method for training neural networks. It is inspired by batch normalization,…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Minibatch Discrimination Minibatch Discrimination is a discriminative technique for generative adversarial networks where we discriminate between whole minibatches of samples rather than between…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

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…

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…

The impact of training dataset size and ensemble inference strategies on head and neck auto-segmentation

2023-03-30 · Edward G. A. Henderson, Marcel van Herk, Eliana M. Vasquez Osorio

Convolutional neural networks (CNNs) are increasingly being used to automate segmentation of organs-at-risk in radiotherapy. Since large sets of highly curated data are scarce, we investigated how much data is required t…

Segmentation

On Scaled Methods for Saddle Point Problems

2022-06-16 · Aleksandr Beznosikov, Aibek Alanov, Dmitry Kovalev, Martin Takáč 외

Methods with adaptive scaling of different features play a key role in solving saddle point problems, primarily due to Adam's popularity for solving adversarial machine learning problems, including GANS training. This pa…

FairGen: Fair Synthetic Data Generation

2022-10-24 · Bhushan Chaudhari, Himanshu Chaudhary, Aakash Agarwal, Kamna Meena 외

With the rising adoption of Machine Learning across the domains like banking, pharmaceutical, ed-tech, etc, it has become utmost important to adopt responsible AI methods to ensure models are not unfairly discriminating …

Fraud DetectionSynthetic Data Generation