Based Augmentation

Based augmentation leverages generative adversarial networks (GANs), and variations like Pix2PixGAN and StyleGAN2-ADA, to synthesize new data points similar to an existing dataset, thereby expanding training sets for machine learning models. Current research focuses on improving GAN architectures to generate higher-quality, more diverse synthetic data, addressing issues like mode collapse and bias amplification, and exploring the effectiveness of these methods across diverse data types, including medical images, audio, and sensor data. This approach is particularly valuable in domains with limited data availability, such as medical imaging and rare event detection, potentially enhancing the performance and generalizability of machine learning models in various scientific and practical applications.

Papers

May 8, 2024

HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis
Zhihan Ju, Wanting Zhou, Longteng Kong, Yu Chen, Yi Li, Zhenan Sun, Caifeng Shan
Medical Image Synthetic Image Medical Image Synthesis Based Augmentation

February 2, 2024

Ambient-Pix2PixGAN for Translating Medical Images from Noisy Data
Wentao Chen, Xichen Xu, Jie Luo, Weimin Zhou
Medical Image Conditional Generative Adversarial Network Noisy Data GAN Architecture Ambient Sound Based Augmentation Medical Image Translation

January 26, 2024

Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification
Oleksandr Fedoruk, Konrad Klimaszewski, Aleksander Ogonowski, Michał Kruk
Generative Adversarial Network GAN Model Covid 19 Based Augmentation

December 29, 2023

Distance Guided Generative Adversarial Network for Explainable Binary Classifications
Xiangyu Xiong, Yue Sun, Xiaohong Liu, Wei Ke, Chan-Tong Lam, Jiangang Chen, Mingfeng Jiang, Mingwei Wang, Hui Xie, Tong Tong, Qinquan Gao, Hao Chen, Tao Tan
Generative Adversarial Network Explainable Classification Based Augmentation

August 23, 2023

A Systematic Study on Quantifying Bias in GAN-Augmented Data
Denis Liu
Generative Adversarial Network Raw Data Adversarial Learning Generative Question Systematic Study Mode Collapse Based Augmentation Quantifying Bias

June 9, 2023

Attention-stacked Generative Adversarial Network (AS-GAN)-empowered Sensor Data Augmentation for Online Monitoring of Manufacturing System
Yuxuan Li, Chenang Liu
Generative Adversarial Network Expert Driven Monitoring GAN Based Manufacturing System Based Augmentation

April 18, 2023

Performance of GAN-based augmentation for deep learning COVID-19 image classification
Oleksandr Fedoruk, Konrad Klimaszewski, Aleksander Ogonowski, Rafał Możdżonek
Data Augmentation System Performance Covid 19 Soft Augmentation Based Augmentation

March 16, 2023

Instance-Conditioned GAN Data Augmentation for Representation Learning
Pietro Astolfi, Arantxa Casanova, Jakob Verbeek, Pascal Vincent, Adriana Romero-Soriano, Michal Drozdzal
Generative Model Data Augmentation Representation Learning Based Augmentation Ct Gan

November 5, 2022

Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data
Mane Margaryan, Matthias Seibold, Indu Joshi, Mazda Farshad, Philipp Fürnstahl, Nassir Navab
Data Augmentation Improved Technique Based Augmentation Audio Augmentation Health Acoustic

November 3, 2022

Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition
Zengrui Jin, Xurong Xie, Mengzhe Geng, Tianzi Wang, Shujie Hu, Jiajun Deng, Guinan Li, Xunying Liu
Speech Recognition Variational Autoencoder Dysarthric Speech Adversarial Data Augmentation Based Augmentation Speech Data Augmentation

August 9, 2022

Generative Data Augmentation Guided by Triplet Loss for Speech Emotion Recognition
Shijun Wang, Hamed Hemati, Jón Guðnason, Damian Borth
Raw Data Speech Emotion Recognition Multilingual Benchmark Triplet Loss Generative Data Augmentation Target Speaker Based Augmentation

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 8, 2022

On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks
Jianqi Yan, Alex P. Leung, David C. Y. Hui
Generative Adversarial Network Super Resolution System Performance Mel Spectrogram Spectrogram Based Gravitational Wave Based Augmentation Glitch Classification

January 12, 2022

Data augmentation through multivariate scenario forecasting in Data Centers using Generative Adversarial Networks
Jaime Pérez, Patricia Arroba, José M. Moya
Generative Adversarial Network Data Augmentation Synthetic Data Data Center Synthetic Time Series Based Augmentation

December 8, 2021

Feature Statistics Mixing Regularization for Generative Adversarial Networks
Junho Kim, Yunjey Choi, Youngjung Uh
Generative Adversarial Network Image Classifier GAN Architecture Bi Discriminator Based Augmentation Feature Mixing

November 29, 2021

Data Augmentation For Medical MR Image Using Generative Adversarial Networks
Panjian Huang, Xu Liu, Yongzhen Huang
Generative Adversarial Network Data Augmentation GAN Model Brain Tumor Magnetic Resonance Image State of the Art GAN Based Augmentation

Based Augmentation

Papers

HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis

Ambient-Pix2PixGAN for Translating Medical Images from Noisy Data

Additional Look into GAN-based Augmentation for Deep Learning COVID-19 Image Classification

Distance Guided Generative Adversarial Network for Explainable Binary Classifications

A Systematic Study on Quantifying Bias in GAN-Augmented Data

Attention-stacked Generative Adversarial Network (AS-GAN)-empowered Sensor Data Augmentation for Online Monitoring of Manufacturing System

Performance of GAN-based augmentation for deep learning COVID-19 image classification

Instance-Conditioned GAN Data Augmentation for Representation Learning

Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data

Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition

Generative Data Augmentation Guided by Triplet Loss for Speech Emotion Recognition

Image Augmentation for Satellite Images

On Improving the Performance of Glitch Classification for Gravitational Wave Detection by using Generative Adversarial Networks

Data augmentation through multivariate scenario forecasting in Data Centers using Generative Adversarial Networks

Feature Statistics Mixing Regularization for Generative Adversarial Networks

Data Augmentation For Medical MR Image Using Generative Adversarial Networks