Generative Adversarial Networks(GAN)는 생성 모델의 한 종류입니다. GAN의 등장이후 생성모델은 매우 빠르게 발전해 오고 있으며 개인적으로 생성모델을 공부한다면 필수적으로 공부해야할 부분중 하나라고 생각합니다. Diffusion model 등 최신 트랜드의 논문들도 GAN을 기반으로 하거나 GAN에서 나온 이론을 토대로 하는 경우가 많습니다.
따라서 필수적으로 읽어야 하는 GAN 관련 논문들을 정리해보려고 합니다. 사실 논문이 워낙 많기 때문에 빠트린 논문들도 많습니다. (계속해서 업데이트 할 생각입니다.) 논문을 볼때는 블로그 리뷰를 읽는 것도 좋지만, 논문의 핵심적인 부분 외에도 자잘한 insight 들과 Tip들이 큰 도움이 되니 웬만하면 논문의 Method 부분은 꼭 읽는 것을 추천드립니다. 그리고 논문을 읽다가 생소한 부분(Auto Encoder, Vector Quantization 등)이 나오면 넘어가지 말고 블로그 리뷰나 reference에 있는 논문을 찾아서 읽으면 큰 도움이 될것 같습니다.
(논문에 대한 설명도 추가할 예정.. 언젠가는..)
GAN (2014)
논문 제목: Generative Adversarial Networks
https://arxiv.org/abs/1406.2661
Generative Adversarial Networks
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that
arxiv.org
CGAN (2014)
논문 제목: Conditional Generative Adversarial Nets
https://arxiv.org/abs/1411.1784
Conditional Generative Adversarial Nets
Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to conditi
arxiv.org
DCGAN (2015)
논문 제목: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://arxiv.org/abs/1511.06434
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between
arxiv.org
Improved GAN (2016)
논문 제목: Improved Techniques for Training GANs
https://arxiv.org/abs/1606.03498
Improved 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 generation of images that humans find
arxiv.org
Pix2Pix (PatchGAN) (2016)
논문 제목: Image-to-Image Translation with Conditional Adversarial Networks
https://arxiv.org/abs/1611.07004
Image-to-Image Translation with Conditional Adversarial Networks
We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This mak
arxiv.org
SRGAN (2016)
논문 제목: Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
https://arxiv.org/abs/1609.04802
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large
arxiv.org
└ Perceptual Loss (2016)
논문 제목: Perceptual Losses for Real-Time Style Transfer and Super-Resolution
https://arxiv.org/abs/1603.08155
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a \emph{per-pixel} loss between the output and ground-tru
arxiv.org
└ StyleTr2 (2021)
논문 제목: Image Style Transfer with Transformers
https://arxiv.org/abs/2105.14576
StyTr$^2$: Image Style Transfer with Transformers
The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content. Owing to the locality in convolutional neural networks (CNNs), extracting and maintaining the global informati
arxiv.org
EBGAN (2016)
논문 제목: Energy-based Generative Adversarial Network
https://arxiv.org/abs/1609.03126
Energy-based Generative Adversarial Network
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions. Similar to the probabi
arxiv.org
WGAN (2017)
논문 제목: Wasserstein GAN
https://arxiv.org/abs/1701.07875
Wasserstein GAN
We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debuggi
arxiv.org
CycleGAN (2017)
논문 제목: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://arxiv.org/abs/1703.10593
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be a
arxiv.org
PGGAN (ProGAN) (2017)
논문 제목: Progressive Growing of GANs for Improved Quality, Stability, and Variation
https://arxiv.org/abs/1710.10196
Progressive Growing of GANs for Improved Quality, Stability, and Variation
We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progr
arxiv.org
UNIT (2017)
논문 제목: Unsupervised Image-to-Image Translation Networks
https://arxiv.org/abs/1703.00848
Unsupervised Image-to-Image Translation Networks
Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive th
arxiv.org
StyleGAN (2018)
논문 제목: A Style-Based Generator Architecture for Generative Adversarial Networks
https://arxiv.org/abs/1812.04948
A Style-Based Generator Architecture for Generative Adversarial Networks
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identit
arxiv.org
└ AdalN (2017)
논문 제목: Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
https://arxiv.org/abs/1703.06868
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical applicat
arxiv.org
MUNIT (2018)
논문 제목: Multimodal Unsupervised Image-to-Image Translation
https://arxiv.org/abs/1804.04732
Multimodal Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation is an important and challenging problem in computer vision. Given an image in the source domain, the goal is to learn the conditional distribution of corresponding images in the target domain, without seeing any pair
arxiv.org
FUNIT (2018)
논문 제목: Few-Shot Unsupervised Image-to-Image Translation
https://arxiv.org/abs/1905.01723
Few-Shot Unsupervised Image-to-Image Translation
Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images. While remarkably successful, current methods require access to man
arxiv.org
StyleGAN2 (2019)
논문 제목: Analyzing and Improving the Image Quality of StyleGAN
https://arxiv.org/abs/1912.04958
Analyzing and Improving the Image Quality of StyleGAN
The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training m
arxiv.org
MSGGAN (2019)
논문 제목: MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
https://arxiv.org/abs/1903.06048
MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
While Generative Adversarial Networks (GANs) have seen huge successes in image synthesis tasks, they are notoriously difficult to adapt to different datasets, in part due to instability during training and sensitivity to hyperparameters. One commonly accep
arxiv.org
Non-saturating GAN (2020)
논문 제목: Non-saturating GAN training as divergence minimization
https://arxiv.org/abs/2010.08029
Non-saturating GAN training as divergence minimization
Non-saturating generative adversarial network (GAN) training is widely used and has continued to obtain groundbreaking results. However so far this approach has lacked strong theoretical justification, in contrast to alternatives such as f-GANs and Wassers
arxiv.org
VQ-GAN (2020)
논문 제목: Taming Transformers for High-Resolution Image Synthesis
https://arxiv.org/abs/2012.09841
Taming Transformers for High-Resolution Image Synthesis
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This makes them expres
arxiv.org
└ VQ-VAE (2017)
논문 제목: Neural Discrete Representation Learning
https://arxiv.org/abs/1711.00937
Neural Discrete Representation Learning
Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEnc
arxiv.org
Drag GAN (2023)
논문 제목: Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
https://arxiv.org/abs/2305.10973
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects. Existing approaches gain controllability of generative adversarial networks (GANs)
arxiv.org
'Generative Models' 카테고리의 다른 글
| [논문 리뷰] Understanding Diffusion Models: A Unified Perspective (3) (0) | 2023.12.11 |
|---|---|
| [논문 리뷰] Understanding Diffusion Models: A Unified Perspective (2) (4) | 2023.08.12 |
| [논문 리뷰] Understanding Diffusion Models: A Unified Perspective (1) (0) | 2023.07.06 |
| [논문 리뷰] StyTr²: Image Style Transfer with Transformers (0) | 2023.06.07 |