Generative Adversarial

Generative Adversarial Networks (GANs) are a class of machine learning models designed to generate new data instances that resemble a training dataset. Current research focuses on improving GAN performance and stability across diverse applications, including image enhancement, speech synthesis, and data augmentation, often employing architectures like HiFi-GAN and variations of GANs combined with other neural network types (e.g., autoencoders, transformers). This work is significant due to GANs' ability to address data scarcity issues, improve the quality of synthetic data for various tasks, and enhance the robustness of AI systems against adversarial attacks.

Papers

April 16, 2023

Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN
Zahra Dehghanian, Saeed Saravani, Maryam Amirmazlaghani, Mohammad Rahmati
Anomaly Detection Generative Adversarial SpOT Robot Adversarial Method

April 9, 2023

FedPNN: One-shot Federated Classification via Evolving Clustering Method and Probabilistic Neural Network hybrid
Polaki Durga Prasad, Yelleti Vivek, Vadlamani Ravi
Synthetic Dataset Generative Adversarial Clustering Method Probabilistic Neural Network One Shot Federated Learning

March 28, 2023

UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation
Dmitrii Torbunov, Yi Huang, Huan-Hsin Tseng, Haiwang Yu, Jin Huang, Shinjae Yoo, Meifeng Lin, Brett Viren, Yihui Ren
Generative Adversarial Unpaired Image to Image Translation

March 27, 2023

Classifier Robustness Enhancement Via Test-Time Transformation
Tsachi Blau, Roy Ganz, Chaim Baskin, Michael Elad, Alex Bronstein
Adversarial Attack Adversarial Training Generative Adversarial

March 24, 2023

Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Shogo Seki
Speech Synthesis Generative Adversarial Synthesized Speech Neural Vocoder HiFi GAN Speech Synthesizer Lightweight Detection

March 19, 2023

Generative Adversarial Classification Network with Application to Network Traffic Classification
Rozhina Ghanavi, Ben Liang, Ali Tizghadam
Application Proficiency Generative Adversarial Imputation Method Traffic Classification Missing Data Imputation Semi Supervised Generative Adversarial Network

February 24, 2023

Data Augmentation with GAN increases the Performance of Arrhythmia Classification for an Unbalanced Dataset
Okan Düzyel, Mehmet Kuntalp
Data Augmentation System Performance Generative Adversarial Imbalanced Data Electrocardiogram Data

February 16, 2023

Generative Adversarial Networks for Malware Detection: a Survey
Aeryn Dunmore, Julian Jang-Jaccard, Fariza Sabrina, Jin Kwak
Timely Survey Generative Adversarial Network GAN Model Generative Adversarial Malware Detection

February 14, 2023

On the Role of Randomization in Adversarially Robust Classification
Lucas Gnecco-Heredia, Yann Chevaleyre, Benjamin Negrevergne, Laurent Meunier, Muni Sreenivas Pydi
Adversarial Attack Adversarial Perturbation Integral Role Generative Adversarial Ensemble Classifier Adversarial Risk Randomization Program Deterministic Learner

February 4, 2023

GAN-based Vertical Federated Learning for Label Protection in Binary Classification
Yujin Han, Leying Guan
Generative Adversarial Network Binary Classification Generative Adversarial Vertical Federated Learning

December 25, 2022

Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image
Samer Kais Jameel, Sezgin Aydin, Nebras H. Ghaeb, Jafar Majidpour, Tarik A. Rashid, Sinan Q. Salih, P. S. JosephNg
Generative Adversarial Network Medical Image Generative Adversarial Conditional Generative Adversarial Network Corneal Image

December 8, 2022

December 7, 2022

PaDPaF: Partial Disentanglement with Partially-Federated GANs
Abdulla Jasem Almansoori, Samuel Horváth, Martin Takáč
Generative Model Generative Adversarial Disentanglement Capability Heterogeneous Client Client Model

November 30, 2022

Generative Adversarial Learning of Sinkhorn Algorithm Initializations
Jonathan Geuter, Vaios Laschos
Optimal Transport Generative Adversarial Sinkhorn Algorithm Self Supervised Loss Entropic Optimal Transport

November 13, 2022

Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing
Jacob J Webber, Cassia Valentini-Botinhao, Evelyn Williams, Gustav Eje Henter, Simon King
Speech Representation Generative Adversarial Neural Vocoder Auto Encoder Mel Spectrogram Differentiable Digital Signal Processing Acoustic Modeling Waveform Generation

November 10, 2022

GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning
Gaku Narita, Junichi Shimizu, Taketo Akama
Generative Adversarial Synthesized Sound Instance Conditioned Adaptation Pitch Extractor

November 2, 2022

October 27, 2022

Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder
Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda
Generative Adversarial Neural Vocoder HiFi GAN Source Filter

Generative Adversarial

Papers

Spot The Odd One Out: Regularized Complete Cycle Consistent Anomaly Detector GAN

FedPNN: One-shot Federated Classification via Evolving Clustering Method and Probabilistic Neural Network hybrid

UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation

Classifier Robustness Enhancement Via Test-Time Transformation

Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis

Generative Adversarial Classification Network with Application to Network Traffic Classification

Data Augmentation with GAN increases the Performance of Arrhythmia Classification for an Unbalanced Dataset

Generative Adversarial Networks for Malware Detection: a Survey

On the Role of Randomization in Adversarially Robust Classification

GAN-based Vertical Federated Learning for Label Protection in Binary Classification

Exploiting the Generative Adversarial Network Approach to Create a Synthetic Topography Corneal Image

Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low Computational Complexity

Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing

PaDPaF: Partial Disentanglement with Partially-Federated GANs

Generative Adversarial Learning of Sinkhorn Algorithm Initializations

Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance Conditioning

Generative Adversarial Training Can Improve Neural Language Models

DSPGAN: a GAN-based universal vocoder for high-fidelity TTS by time-frequency domain supervision from DSP

Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder