Novel Domain Adaptation

Novel domain adaptation tackles the challenge of transferring knowledge learned from a labeled data source to an unlabeled target domain with differing characteristics. Current research emphasizes techniques like contrastive learning, which focuses on learning domain-invariant features, and the use of attention mechanisms to highlight discriminative information. These methods are applied across diverse fields, including time series analysis, image classification, and natural language processing, improving model performance in scenarios with limited labeled data for the target domain. The resulting advancements have significant implications for various applications where labeled data is scarce or expensive to obtain, enhancing the generalizability and robustness of machine learning models.

Papers

October 18, 2024

AC-Mix: Self-Supervised Adaptation for Low-Resource Automatic Speech Recognition using Agnostic Contrastive Mixup
Carlos Carvalho, Alberto Abad
Self Supervised Adaptation Concern Low Resource Recognition Rate Novel Domain Adaptation

July 23, 2024

EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principles
Zicheng Pan, Xiaohan Yu, Yongsheng Gao
Latent Space Source Free Domain Adaptation Fine Grained Visual Frame Attention Class Separation Social Class Novel Domain Adaptation

April 17, 2024

DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series
Zahra Zamanzadeh Darban, Yiyuan Yang, Geoffrey I. Webb, Charu C. Aggarwal, Qingsong Wen, Mahsa Salehi
Anomaly Detection Domain Adaptation Unsupervised Domain Adaptation Multivariate Time Series Contrastive Domain Adaptation Novel Domain Adaptation

January 24, 2024

Weakly supervised covariance matrices alignment through Stiefel matrices estimation for MEG applications
Antoine Collas, Rémi Flamary, Alexandre Gramfort
Global Mixing Covariance Alignment Domain Mixing Novel Domain Adaptation Matrix Estimation Magnetoencephalography Data

October 7, 2023

Integrating Contrastive Learning into a Multitask Transformer Model for Effective Domain Adaptation
Chung-Soo Ahn, Jagath C. Rajapakse, Rajib Rana
Large Language Model Contrastive Learning Speech Emotion Recognition Multi Task Transformer Cross Corpus Novel Domain Adaptation

September 15, 2023

T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds
Awet Haileslassie Gebrehiwot, David Hurych, Karel Zimmermann, Patrick Pérez, Tomáš Svoboda
Point Cloud Domain Adaptation Unsupervised Domain Adaptation 3D Semantic Segmentation Deep Learning Based Perception Novel Domain Adaptation

May 31, 2023

February 17, 2023

Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning
Lei Tian, Yongqiang Tang, Liangchen Hu, Wensheng Zhang
Domain Adaptation Label Propagation Semi Supervised Domain Adaptation Novel Domain Adaptation

December 7, 2022

Cyclically Disentangled Feature Translation for Face Anti-spoofing
Haixiao Yue, Keyao Wang, Guosheng Zhang, Haocheng Feng, Junyu Han, Errui Ding, Jingdong Wang
Domain Adaptation Adversarial Training Face Anti Spoofing Feature Transfer Liveness Detection Multi Target Domain Adaptation Novel Domain Adaptation

December 2, 2022

Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment
Qizhou Wang, Guansong Pang, Mahsa Salehi, Wray Buntine, Christopher Leckie
Anomaly Detection Graph Anomaly Detection Contrastive Alignment Novel Domain Adaptation Anomaly Aware

November 22, 2022

Anatomy-guided domain adaptation for 3D in-bed human pose estimation
Alexander Bigalke, Lasse Hansen, Jasper Diesel, Carlotta Hennigs, Philipp Rostalski, Mattias P. Heinrich
Domain Adaptation Estimation Task Source Free Domain Adaptation Pose Estimation Network Plausible Pose Novel Domain Adaptation Bed Human

September 23, 2022

Robust Domain Adaptation for Machine Reading Comprehension
Liang Jiang, Zhenyu Huang, Jia Liu, Zujie Wen, Xi Peng
Domain Adaptation Machine Reading Comprehension Novel Domain Adaptation Robust Domain Adaptation

Novel Domain Adaptation

Papers

AC-Mix: Self-Supervised Adaptation for Low-Resource Automatic Speech Recognition using Agnostic Contrastive Mixup

EIANet: A Novel Domain Adaptation Approach to Maximize Class Distinction with Neural Collapse Principles

DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series

Weakly supervised covariance matrices alignment through Stiefel matrices estimation for MEG applications

Integrating Contrastive Learning into a Multitask Transformer Model for Effective Domain Adaptation

T-UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds

Building Manufacturing Deep Learning Models with Minimal and Imbalanced Training Data Using Domain Adaptation and Data Augmentation

Deep into The Domain Shift: Transfer Learning through Dependence Regularization

Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning

Cyclically Disentangled Feature Translation for Face Anti-spoofing

Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment

Anatomy-guided domain adaptation for 3D in-bed human pose estimation

Robust Domain Adaptation for Machine Reading Comprehension