GAN Architecture

Generative Adversarial Networks (GANs) are a class of deep learning models designed to generate new data instances that resemble a training dataset. Current research focuses on improving GAN architectures to address challenges like training instability, mode collapse, and the need for large datasets, exploring variations such as conditional GANs (cGANs), and incorporating techniques like hypernetworks and downstream feedback. These advancements are significantly impacting diverse fields, enabling applications ranging from medical image enhancement and data augmentation to synthetic data generation for improving model fairness and efficiency in computationally intensive simulations.

Papers

May 22, 2023

Phased Data Augmentation for Training a Likelihood-Based Generative Model with Limited Data
Yuta Mimura
Generative Model Data Augmentation GAN Model Limited Data Data Augmentation Technique GAN Architecture Likelihood Based Generative

April 22, 2023

Physics-guided generative adversarial network to learn physical models
Kazuo Yonekura
Generative Adversarial Network Physic Informed Neural Network Neural Network Model C Gan GAN Architecture Physical Model

March 25, 2023

Spatial Latent Representations in Generative Adversarial Networks for Image Generation
Maciej Sypetkowski
Generative Adversarial Network Latent Space Image Generation GAN Architecture

March 15, 2023

Copyright Protection and Accountability of Generative AI:Attack, Watermarking and Attribution
Haonan Zhong, Jiamin Chang, Ziyue Yang, Tingmin Wu, Pathum Chamikara Mahawaga Arachchige, Chehara Pathmabandu, Minhui Xue
Generative Adversarial Network Generative AI GAN Model Agnostic Watermarking Source Attribution GAN Architecture Copyright Protection Model Watermarking

March 9, 2023

Scaling up GANs for Text-to-Image Synthesis
Minguk Kang, Jun-Yan Zhu, Richard Zhang, Jaesik Park, Eli Shechtman, Sylvain Paris, Taesung Park
GAN Model Text to Image Synthesis GAN Architecture Generative Image Model Large Scale Generative Model

February 17, 2023

Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey
Shiv Ram Dubey, Satish Kumar Singh
Generative Adversarial Network Computer Vision Comprehensive Survey GAN Architecture Transformer Based Generative Adversarial

January 31, 2023

GANravel: User-Driven Direction Disentanglement in Generative Adversarial Networks
Noyan Evirgen, Xiang 'Anthony' Chen
Generative Adversarial Network GAN Architecture Text Guided Editing Concept Disentanglement

January 27, 2023

HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
Adam Kania, Artur Kasymov, Maciej Zięba, Przemysław Spurek
Generative Model Neural Radiance Field GAN Architecture Hypernetwork Approach NeRF GAN Hyper Convolution

December 20, 2022

End to End Generative Meta Curriculum Learning For Medical Data Augmentation
Meng Li, Brian Lovell
Generative Adversarial Network Data Augmentation Curriculum Learning GAN Architecture Annotated End State Synthetic Medical Image

December 18, 2022

GAN-based Tabular Data Generator for Constructing Synopsis in Approximate Query Processing: Challenges and Solutions
Mohammadali Fallahian, Mohsen Dorodchi, Kyle Kreth
Generative Adversarial Network Technical Challenge Tabular Data Solution Path GAN Architecture GAN Algorithm Story Summarization

November 5, 2022

Disentangling Content and Motion for Text-Based Neural Video Manipulation
Levent Karacan, Tolga Kerimoğlu, İsmail İnan, Tolga Birdal, Erkut Erdem, Aykut Erdem
Latent Representation Motion Information Hierarchical Representation GAN Architecture Semantic Editing Video Manipulation

November 2, 2022

Autoregressive GAN for Semantic Unconditional Head Motion Generation
Louis Airale, Xavier Alameda-Pineda, Stéphane Lathuilière, Dominique Vaufreydaz
Head Generation GAN Architecture Head Motion Autoregressive Generative Model

October 25, 2022

Mitigating Health Data Poverty: Generative Approaches versus Resampling for Time-series Clinical Data
Raffaele Marchesi, Nicolo Micheletti, Giuseppe Jurman, Venet Osmani
GAN Model Generative Approach GAN Architecture Data Challenge Clinical Time Series

October 24, 2022

FairGen: Fair Synthetic Data Generation
Bhushan Chaudhari, Himanshu Chaudhary, Aakash Agarwal, Kamna Meena, Tanmoy Bhowmik
GAN Model Generative Adversarial GAN Architecture Fair Synthetic

September 7, 2022

Supervised GAN Watermarking for Intellectual Property Protection
Jianwei Fei, Zhihua Xia, Benedetta Tondi, Mauro Barni
Generative Adversarial Network GAN Model GAN Architecture Intellectual Property Protection Adversarial Watermarking

July 29, 2022

Image Augmentation for Satellite Images
Oluwadara Adedeji, Peter Owoade, Opeyemi Ajayi, Olayiwola Arowolo
Generative Model GAN Model Satellite Image Image Augmentation GAN Architecture Deep Learning Classification Based Augmentation

July 3, 2022

Data-Driven Modeling of Noise Time Series with Convolutional Generative Adversarial Networks
Adam Wunderlich, Jack Sklar
Generative Adversarial Network Time Series GAN Architecture Data Driven Modeling

June 29, 2022

SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations
Jinsung Jeon, Noseong Park
C Gan Score Based Generative Denoising Diffusion GAN Architecture

June 24, 2022

MULTI-FLGANs: Multi-Distributed Adversarial Networks for Non-IID distribution
Akash Amalan, Rui Wang, Yanqi Qiao, Emmanouil Panaousis, Kaitai Liang
GAN Model Product Distribution GAN Architecture

May 31, 2022

PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras
Generative Adversarial Network Unsupervised Learning Saliency Map GAN Architecture Feature Map Part Identification Red PANDA