Domain Adversarial

Domain adversarial training aims to improve the generalization of machine learning models by mitigating the impact of data distribution shifts between different domains (e.g., different recording environments, image styles, or sensor types). Current research focuses on adapting various model architectures, including generative adversarial networks (GANs), variational autoencoders (VAEs), and neural processes, often incorporating techniques like adversarial learning, active learning, and representation alignment to achieve domain invariance. This approach is significant because it enhances the robustness and reliability of machine learning models across diverse real-world applications, ranging from speech recognition and image classification to hydrological prediction and medical image analysis.

Papers

November 5, 2024

Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training
Junhao Dong, Xinghua Qu, Z. Jane Wang, Yew-Soon Ong
Adversarial Example Adversarial Training Adversarial Robustness Domain Adversarial

October 19, 2024

Unsupervised Domain Adaptation Approaches for Chessboard Recognition
Wassim Jabbour, Enzo Benoit-Jeannin, Oscar Bedford, Saif Shahin
Domain Adaptation Supervised ImageNet Unsupervised Domain Adaptation Domain Adversarial Domain Discriminator

September 19, 2024

Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition
Chien-Chun Wang, Li-Wei Chen, Cheng-Kang Chou, Hung-Shin Lee, Berlin Chen, Hsin-Min Wang
Speech Recognition Domain Adversarial Differentiable Channel Pre Trained Automatic Speech Recognition

August 23, 2024

Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling
Zongyao Lyu, William J. Beksi
Active Learning Semi Supervised Variational Autoencoder Adversarial Learning Pseudo Labeling Stable Rank Domain Adversarial Semi Supervised Active Learning

July 24, 2024

Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning
Hayato Watahiki, Ryo Iwase, Ryosuke Unno, Yoshimasa Tsuruoka
Behavior Cloning Domain Adversarial Representation Alignment Domain Translation Cross Domain Alignment Cross Domain Policy Transfer

July 3, 2024

A Geometric Framework for Adversarial Vulnerability in Machine Learning
Brian Bell
Machine Learning Adversarial Attack Adversarial Perturbation Adversarial Vulnerability Domain Adversarial Manifold Hypothesis Geometric Framework

June 2, 2024

Extrapolability Improvement of Machine Learning-Based Evapotranspiration Models via Domain-Adversarial Neural Networks
Haiyang Shi
New Machine Domain Adversarial Extrapolation Performance Extrapolation Capability

May 28, 2024

Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process
Sophia Sun, Wenyuan Chen, Zihao Zhou, Sonia Fereidooni, Elise Jortberg, Rose Yu
Adversarial Training Data Driven Neural Process Domain Adversarial

April 19, 2024

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
Heqi Peng, Yunhong Wang, Ruijie Yang, Beichen Li, Rui Wang, Yuanfang Guo
Adversarial Attack Adversarial Example Stronger Generalizability Domain Adversarial Adversarial Domain Adaptation Adversarial Example Detection

April 9, 2024

Towards Robust Domain Generation Algorithm Classification
Arthur Drichel, Marc Meyer, Ulrike Meyer
Adversarial Training Domain Adversarial Domain Generation Algorithm

March 27, 2024

SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks
Brian Formento, Wenjie Feng, Chuan Sheng Foo, Luu Anh Tuan, See-Kiong Ng
Adversarial Attack Adversarial Training Meaningful Representation Domain Adversarial Word Level Attack

March 14, 2024

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
Atif Belal, Akhil Meethal, Francisco Perdigon Romero, Marco Pedersoli, Eric Granger
Domain Adaptation Attention Based Domain Adversarial Multi Source Domain Adaptation

March 10, 2024

Domain Adversarial Active Learning for Domain Generalization Classification
Jianting Chen, Ling Ding, Yunxiao Yang, Zaiyuan Di, Yang Xiang
Domain Generalization Domain Adversarial Domain Generalization Datasets

January 27, 2024

Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training
Haesun Joung, Kyogu Lee
Music Industry Music Information Retrieval Domain Adversarial Audio Data Music Tagging

December 22, 2023

The Rate-Distortion-Perception-Classification Tradeoff: Joint Source Coding and Modulation via Inverse-Domain GANs
Junli Fang, João F. C. Mota, Baoshan Lu, Weicheng Zhang, Xuemin Hong
Generative Model Image Compression Domain Adversarial Digital Modulation Joint Source Channel Coding Rate Distortion Perception Channel Coding

December 20, 2023

Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection
Xisheng Li, Wei Li, Pinhao Song, Mingjun Zhang, Jie Zhou
Data Augmentation Domain Shift Underwater Environment Internet Service Domain Domain Adversarial Underwater Object Detection

December 16, 2023

Annotation-free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusion
Gakusei Sato, Taketo Akama
Synthetic Data Audio Processing Music Transcription Domain Adversarial Synthesized Sound Single Channel Audio

November 16, 2023

Evolving Domain Adaptation of Pretrained Language Models for Text Classification
Yun-Shiuan Chuang, Yi Wu, Dhruv Gupta, Rheeya Uppaal, Ananya Kumar, Luhang Sun, Makesh Narsimhan Sreedhar, Sijia Yang, Timothy T. Rogers, Junjie Hu
Domain Adaptation Pre Trained Language Model Text Classification Pretrained Language Model Domain Adaptive Domain Adversarial

October 21, 2023

Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment
Chuang Zhao, Hongke Zhao, Hengshu Zhu, Zhenya Huang, Nan Feng, Enhong Chen, Hui Xiong
Unsupervised Domain Adaptation Adversarial Learning Domain Adversarial Domain Discriminator Bi Discriminator

August 27, 2023

Multi-Subdomain Adversarial Network for Cross-Subject EEG-based Emotion Recognition
Guang Lin, Jianhai Zhang
Domain Adaptation Emotion Recognition Adversarial Learning Domain Adversarial Domain Discrepancy

Domain Adversarial

Papers

Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training

Unsupervised Domain Adaptation Approaches for Chessboard Recognition

Channel-Aware Domain-Adaptive Generative Adversarial Network for Robust Speech Recognition

Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling

Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning

A Geometric Framework for Adversarial Vulnerability in Machine Learning

Extrapolability Improvement of Machine Learning-Based Evapotranspiration Models via Domain-Adversarial Neural Networks

Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation

Towards Robust Domain Generation Algorithm Classification

SemRoDe: Macro Adversarial Training to Learn Representations That are Robust to Word-Level Attacks

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors

Domain Adversarial Active Learning for Domain Generalization Classification

Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training

The Rate-Distortion-Perception-Classification Tradeoff: Joint Source Coding and Modulation via Inverse-Domain GANs

Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection

Annotation-free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusion

Evolving Domain Adaptation of Pretrained Language Models for Text Classification

Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment

Multi-Subdomain Adversarial Network for Cross-Subject EEG-based Emotion Recognition