Adversarial Data Augmentation

Adversarial data augmentation (ADA) enhances the robustness and generalization of machine learning models by generating synthetic training data designed to challenge the model's assumptions. Current research focuses on tailoring ADA to specific data types (e.g., time series, images, speech) and tasks (e.g., face recognition, speaker verification, medical image segmentation), often employing generative adversarial networks (GANs) or other differentiable transformation methods to create these adversarial examples. This approach is proving valuable across diverse fields, improving model performance in challenging conditions such as low-quality inputs, domain shifts, and noisy data, ultimately leading to more reliable and robust AI systems.

Papers

July 21, 2024

TADA: Temporal Adversarial Data Augmentation for Time Series Data
Byeong Tak Lee, Joon-myoung Kwon, Yong-Yeon Jo
Time Series Data Temporal Shift Adversarial Data Augmentation Time Augmentation Time Warp

July 20, 2024

ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition
Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Ali Dabouei, Nasser M. Nasrabadi
Native Robustness Face Recognition Face Alignment Synthetic Sample Adversarial Data Augmentation Spatial Transformation

March 12, 2024

Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation
Chengxing Jia, Fuxiang Zhang, Yi-Chen Li, Chen-Xiao Gao, Xu-Hui Liu, Lei Yuan, Zongzhang Zhang, Yang Yu
Contrastive Learning Adversarial Example Health Policy Recommendation Task Specification Task Representation Adversarial Data Augmentation Offline Meta Reinforcement Learning Offline Visual Representation Learning

February 5, 2024

Adversarial Data Augmentation for Robust Speaker Verification
Zhenyu Zhou, Junhui Chen, Namin Wang, Lantian Li, Dong Wang
Data Augmentation Adversarial Learning Speaker Embeddings Adversarial Data Augmentation Robust Speaker Verification

January 1, 2024

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation
Huimeng Wang, Zengrui Jin, Mengzhe Geng, Shujie Hu, Guinan Li, Tianzi Wang, Haoning Xu, Xunying Liu
Automatic Speech Recognition Dysarthric Speech Dysarthric Speech Recognition Adversarial Data Augmentation

October 11, 2023

ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data Fusion
Jinghui Qin, Lihuang Fang, Ruitao Lu, Liang Lin, Yukai Shi
Hyperspectral Image Image Fusion Hyperspectral Imaging Hyperspectral Datasets Adversarial Data Augmentation Adversarial Style Augmentation Learning Based Hyperspectral

July 6, 2023

ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images
Mokshagna Sai Teja Karanam, Tushar Kataria, Krithika Iyer, Shireen Elhabian
Statistical Shape Shape Representation Augmented Sample Adversarial Data Augmentation Shape Model

March 17, 2023

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation
Devavrat Tomar, Guillaume Vray, Behzad Bozorgtabar, Jean-Philippe Thiran
Test Time Adaptation Test Time Adversarial Augmentation Adversarial Data Augmentation Test Loss

February 25, 2023

Deep Learning-based Multi-Organ CT Segmentation with Adversarial Data Augmentation
Shaoyan Pan, Shao-Yuan Lo, Min Huang, Chaoqiong Ma, Jacob Wynne, Tonghe Wang, Tian Liu, Xiaofeng Yang
Adversarial Attack Adversarial Noise Multi Organ Segmentation Adversarial Feature Adversarial Data Augmentation Adversarial Style Augmentation

November 13, 2022

Adversarial and Random Transformations for Robust Domain Adaptation and Generalization
Liang Xiao, Jiaolong Xu, Dawei Zhao, Erke Shang, Qi Zhu, Bin Dai
Data Augmentation Strong Generalization Adversarial Example Adversarial Text Adversarial Augmentation Random Transformation Adversarial Data Augmentation Robust Domain Adaptation Random Data Augmentation

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

November 2, 2022

Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach
Kaiwen Yang, Yanchao Sun, Jiahao Su, Fengxiang He, Xinmei Tian, Furong Huang, Tianyi Zhou, Dacheng Tao
Data Augmentation Representation Learning Adversarial Data Augmentation

August 24, 2022

Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation
Qiyuan Chen, Raed Al Kontar, Maher Nouiehed, Jessie Yang, Corey Lester
Deep Learning Adversarial Example Cost Sensitive Adversarial Data Augmentation Price Sensitivity

May 2, 2022

Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
Zhenwei Tang, Shichao Pei, Zhao Zhang, Yongchun Zhu, Fuzhen Zhuang, Robert Hoehndorf, Xiangliang Zhang
LeArning Abstract Knowledge Graph Completion Positive Unlabeled Learning Adversarial Data Augmentation Negative Learning Minimax Game

April 15, 2022

CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation
Md Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais, Pascal Poupart
Contrastive Learning Knowledge Distillation Data Augmentation Adversarial Training Adversarial Data Augmentation Contrastive Augmentation

December 5, 2021

RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather
Jialu Wang, Muhamad Risqi U. Saputra, Chris Xiaoxuan Lu, Niki Trigon, Andrew Markham
Data Augmentation State of the Art Adverse Weather Augmentation Method Camera Localization Adversarial Data Augmentation

Adversarial Data Augmentation

Papers

TADA: Temporal Adversarial Data Augmentation for Time Series Data

ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition

Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation

Adversarial Data Augmentation for Robust Speaker Verification

Enhancing Pre-trained ASR System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation

ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data Fusion

ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Deep Learning-based Multi-Organ CT Segmentation with Adversarial Data Augmentation

Adversarial and Random Transformations for Robust Domain Adaptation and Generalization

Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition

Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach

Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation

Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion

CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation

RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather