All Projects → fjxmlzn → Pacgan

fjxmlzn / Pacgan

Licence: mit
[NeurIPS 2018] [JSAIT] PacGAN: The power of two samples in generative adversarial networks

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Pacgan

Gans In Action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
Stars: ✭ 748 (+1016.42%)
Mutual labels:  gan, generative-adversarial-network, gans
Iseebetter
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
Stars: ✭ 202 (+201.49%)
Mutual labels:  gan, generative-adversarial-network, gans
Cyclegan
Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
Stars: ✭ 10,933 (+16217.91%)
Mutual labels:  gan, generative-adversarial-network, gans
Generative adversarial networks 101
Keras implementations of Generative Adversarial Networks. GANs, DCGAN, CGAN, CCGAN, WGAN and LSGAN models with MNIST and CIFAR-10 datasets.
Stars: ✭ 138 (+105.97%)
Mutual labels:  gan, generative-adversarial-network, gans
DLSS
Deep Learning Super Sampling with Deep Convolutional Generative Adversarial Networks.
Stars: ✭ 88 (+31.34%)
Mutual labels:  generative-adversarial-network, gan, gans
Tagan
An official PyTorch implementation of the paper "Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language", NeurIPS 2018
Stars: ✭ 97 (+44.78%)
Mutual labels:  gan, generative-adversarial-network, gans
A Pytorch Tutorial To Super Resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution
Stars: ✭ 157 (+134.33%)
Mutual labels:  gan, generative-adversarial-network, gans
Doppelganger
[IMC 2020 (Best Paper Finalist)] Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
Stars: ✭ 97 (+44.78%)
Mutual labels:  gan, generative-adversarial-network, gans
AvatarGAN
Generate Cartoon Images using Generative Adversarial Network
Stars: ✭ 24 (-64.18%)
Mutual labels:  generative-adversarial-network, gan, gans
Gif
GIF is a photorealistic generative face model with explicit 3D geometric and photometric control.
Stars: ✭ 233 (+247.76%)
Mutual labels:  gan, generative-adversarial-network, gans
Pytorch Cyclegan And Pix2pix
Image-to-Image Translation in PyTorch
Stars: ✭ 16,477 (+24492.54%)
Mutual labels:  gan, generative-adversarial-network, gans
Sdv
Synthetic Data Generation for tabular, relational and time series data.
Stars: ✭ 360 (+437.31%)
Mutual labels:  gan, generative-adversarial-network, gans
Faceswap Gan
A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.
Stars: ✭ 3,099 (+4525.37%)
Mutual labels:  gan, generative-adversarial-network, gans
Anycost Gan
[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing
Stars: ✭ 367 (+447.76%)
Mutual labels:  gan, generative-adversarial-network, gans
Instagan
InstaGAN: Instance-aware Image Translation (ICLR 2019)
Stars: ✭ 761 (+1035.82%)
Mutual labels:  gan, generative-adversarial-network
Anime Inpainting
An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复,去马赛克,填补,去瑕疵
Stars: ✭ 761 (+1035.82%)
Mutual labels:  gan, generative-adversarial-network
Cyclegan Tensorflow
An implementation of CycleGan using TensorFlow
Stars: ✭ 1,096 (+1535.82%)
Mutual labels:  gan, generative-adversarial-network
Acgan Pytorch
Pytorch implementation of Conditional Image Synthesis with Auxiliary Classifier GANs
Stars: ✭ 57 (-14.93%)
Mutual labels:  gan, generative-adversarial-network
Pytorch Pretrained Biggan
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
Stars: ✭ 779 (+1062.69%)
Mutual labels:  gan, generative-adversarial-network
Musegan
An AI for Music Generation
Stars: ✭ 794 (+1085.07%)
Mutual labels:  gan, generative-adversarial-network

PacGAN: The power of two samples in generative adversarial networks

[paper (arXiv)] [paper (NeurIPS)] [paper (JSAIT)] [poster] [website] [interview (youtube)] [code]

Authors: Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh

Abstract: Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little diversity, even when trained on diverse datasets. This phenomenon, known as mode collapse, has been the main focus of several recent advances in GANs. Yet there is little understanding of why mode collapse happens and why existing approaches are able to mitigate mode collapse. We propose a principled approach to handling mode collapse, which we call packing. The main idea is to modify the discriminator to make decisions based on multiple samples from the same class, either real or artificially generated. We borrow analysis tools from binary hypothesis testing---in particular the seminal result of Blackwell [Bla53]---to prove a fundamental connection between packing and mode collapse. We show that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process. Numerical experiments on benchmark datasets suggests that packing provides significant improvements in practice as well.

Codes for reproducing results in paper

Prerequisites

The codes are based on GPUTaskScheduler library. Please install it first.

Code list

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].