F GAN

F-GANs are a class of generative adversarial networks (GANs) that leverage f-divergences to measure the discrepancy between a generated and a target data distribution, aiming to improve the quality and stability of synthetic data generation. Current research focuses on refining f-divergence optimization techniques, exploring variations like (f,Γ)-GANs and dual-objective GANs to address training instabilities and improve performance, and applying these models to diverse applications such as image synthesis and time-series data generation. This work is significant because it enhances the theoretical understanding and practical capabilities of GANs, leading to improved synthetic data generation for various scientific and engineering domains.

Papers

September 15, 2024

A Simpler Alternative to Variational Regularized Counterfactual Risk Minimization
Hua Chang Bakker, Shashank Gupta, Harrie Oosterhuis
Policy Learning Divergence Regularization F GAN Counterfactual Metric

June 24, 2024

Concentration Inequalities for $(f,\Gamma)$-GANs
Jeremiah Birrell
Generative Adversarial Network Adversarial Learning Generative Question Concentration Inequality F GAN

May 15, 2024

f-GAN: A frequency-domain-constrained generative adversarial network for PPG to ECG synthesis
Nathan C. L. Kong, Dae Lee, Huyen Do, Dae Hoon Park, Cong Xu, Hongda Mao, Jonathan Chung
PPG Signal Photoplethysmography Data ECG Signal Heart Rate Estimation F GAN

October 27, 2023

Addressing GAN Training Instabilities via Tunable Classification Losses
Monica Welfert, Gowtham R. Kurri, Kyle Otstot, Lalitha Sankar
GAN Training GAN Loss F GAN

April 9, 2023

ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis
Ivan Ferreira-Chacua, Ardiansyah Koeshidayatullah
Deep Learning New Paradigm F GAN

February 1, 2023

Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach
Yong Xiao, Rong Xia, Yingyu Li, Guangming Shi, Diep N. Nguyen, Dinh Thai Hoang, Dusit Niyato, Marwan Krunz
Generative Adversarial Network Classification Code Network Traffic Edge Network Federated Self Supervised Learning F GAN

October 20, 2022

Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN
Hamza Bouzid, Lahoucine Ballihi
Facial Expression GAN Generated Face F GAN

September 14, 2022

Asymptotic Statistical Analysis of $f$-divergence GAN
Xinwei Shen, Kani Chen, Tong Zhang
Generative Adversarial Network Asymptotic Inference F GAN

August 18, 2022

T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up
Deyin Liu, Lin Yuanbo Wu, Bo Li, Zongyuan Ge
C Gan Text to Image Generation Model Image Generation Task Person Image Generation F GAN Manifold Mixup

May 11, 2022

A Unified f-divergence Framework Generalizing VAE and GAN
Jaime Roquero Gimenez, James Zou
GAN Model F$ Divergence F GAN

F GAN

Papers

A Simpler Alternative to Variational Regularized Counterfactual Risk Minimization

Concentration Inequalities for $(f,\Gamma)$-GANs

f-GAN: A frequency-domain-constrained generative adversarial network for PPG to ECG synthesis

Addressing GAN Training Instabilities via Tunable Classification Losses

ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis

Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach

Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN

Asymptotic Statistical Analysis of $f$-divergence GAN

T-Person-GAN: Text-to-Person Image Generation with Identity-Consistency and Manifold Mix-Up

A Unified f-divergence Framework Generalizing VAE and GAN