GAN Training

GAN training aims to stabilize and improve the performance of Generative Adversarial Networks, which generate realistic data by pitting a generator against a discriminator in a minimax game. Current research focuses on novel loss functions, regularization techniques (e.g., Lipschitz continuity constraints, score matching), and architectural modifications to address issues like mode collapse, overfitting (especially with limited data), and training instability. These advancements are significant because they enhance the quality and diversity of generated data, impacting diverse fields such as medical imaging, video generation, and image editing, where high-fidelity synthetic data is crucial for various applications.

Papers

October 19, 2022

Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis
Ruinan Jin, Xiaoxiao Li
Backdoor Attack Generative Adversarial GAN Training Adversarial Behavior

October 11, 2022

FreGAN: Exploiting Frequency Components for Training GANs under Limited Data
Mengping Yang, Zhe Wang, Ziqiu Chi, Yanbing Zhang
GAN Model Limited Data GAN Training Low Frequency High Quality Generation Frequency Component

October 9, 2022

Dissecting adaptive methods in GANs
Samy Jelassi, David Dobre, Arthur Mensch, Yuanzhi Li, Gauthier Gidel
Generative Adversarial Network GAN Training Adaptive Method

October 7, 2022

Adversarial network training using higher-order moments in a modified Wasserstein distance
Oliver Serang
Generative Adversarial Network Adversarial Training Wasserstein Distance GAN Training Wasserstein Space Order Moment

October 6, 2022

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection
Rizwan Hamid Randhawa, Nauman Aslam, Mohammad Alauthman, Muhammad Khalid, Husnain Rafiq
Deep Reinforcement Learning GAN Training Adversarial Evasion Attack BotNet Detection

September 26, 2022

DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physics
Tom Dooney, Stefano Bromuri, Lyana Curier
GAN Training Gravitational Wave Time Domain GAN Structure

September 25, 2022

Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting
Parth Kothari, Alexandre Alahi
Generative Adversarial GAN Training Human Trajectory Adversarial Machine Learning Multimodal Future Trajectory

September 6, 2022

DC-Art-GAN: Stable Procedural Content Generation using DC-GANs for Digital Art
Rohit Gandikota, Nik Bear Brown
C Gan Procedural Content Generation GAN Training Deep Generative Digital Art

September 5, 2022

Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation
Yen-Tung Yeh, Bo-Yu Chen, Yi-Hsuan Yang
Generative Adversarial Network GAN Model GAN Training Loop Generation Projected GAN

August 26, 2022

Learning From Positive and Unlabeled Data Using Observer-GAN
Omar Zamzam, Haleh Akrami, Richard Leahy
LeArning Abstract Generative Adversarial Network Unlabeled Data GAN Training Positive Emotional Language GAN Algorithm GAN Discriminator Learning Based Observer

August 21, 2022

Instability and Local Minima in GAN Training with Kernel Discriminators
Evan Becker, Parthe Pandit, Sundeep Rangan, Alyson K. Fletcher
Generative Adversarial Network Generative Modeling Core Stability GAN Training Mode Collapse Local Minimum Kernel Classification Point Model

August 12, 2022

Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations
Vincent Dumont, Xiangyang Ju, Juliane Mueller
Generative Adversarial Network GAN Model Hyperparameter Optimization Generative Adversarial GAN Training

July 25, 2022

Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks
Massimiliano Lupo Pasini, Junqi Yin
Conditional Generative Adversarial Network GAN Training ImageNet 1k GAN Based Wasserstein Generative Adversarial Network

June 16, 2022

On Scaled Methods for Saddle Point Problems
Aleksandr Beznosikov, Aibek Alanov, Dmitry Kovalev, Martin Takáč, Alexander Gasnikov
GAN Model GAN Training Saddle Point Learning Problem Scaling Method

June 15, 2022

GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds
Jianfeng Xiang, Jiaolong Yang, Yu Deng, Xin Tong
Image Generation GAN Model High Resolution GAN Training 3D Aware GAN Radiance Manifold

May 24, 2022

Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance
Jianhan Wu, Shijing Si, Jianzong Wang, Jing Xiao
GAN Model Synthetic Image Image Synthesis Wasserstein Distance GAN Training

May 5, 2022

Generative Adversarial Network Based Synthetic Learning and a Novel Domain Relevant Loss Term for Spine Radiographs
Ethan Schonfeld, Anand Veeravagu
Generative Adversarial Network GAN Training GAN Generator Spinal X Ray Domain Loss

April 19, 2022

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations
Atsuhiro Noguchi, Xiao Sun, Stephen Lin, Tatsuya Harada
High Efficiency Unsupervised Learning GAN Training

April 10, 2022

Multi-Label Clinical Time-Series Generation via Conditional GAN
Chang Lu, Chandan K. Reddy, Ping Wang, Dong Nie, Yue Ning
Generative Adversarial Network Time Series GAN Training Conditional GAN Synthetic EHR

February 17, 2022

When, Why, and Which Pretrained GANs Are Useful?
Timofey Grigoryev, Andrey Voynov, Artem Babenko
Pre Trained GAN Training

GAN Training

Papers

Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis

FreGAN: Exploiting Frequency Components for Training GANs under Limited Data

Dissecting adaptive methods in GANs

Adversarial network training using higher-order moments in a modified Wasserstein distance

Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detection

DVGAN: Stabilize Wasserstein GAN training for time-domain Gravitational Wave physics

Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting

DC-Art-GAN: Stable Procedural Content Generation using DC-GANs for Digital Art

Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop Generation

Learning From Positive and Unlabeled Data Using Observer-GAN

Instability and Local Minima in GAN Training with Kernel Discriminators

Hyperparameter Optimization of Generative Adversarial Network Models for High-Energy Physics Simulations

Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks

On Scaled Methods for Saddle Point Problems

GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds

Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance

Generative Adversarial Network Based Synthetic Learning and a Novel Domain Relevant Loss Term for Spine Radiographs

Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations

Multi-Label Clinical Time-Series Generation via Conditional GAN

When, Why, and Which Pretrained GANs Are Useful?