Two stages domain invariant representation learners solve the large co-variate shift in unsupervised domain adaptation with two dimensional data domains

Recent developments in the unsupervised domain adaptation (UDA) enable the unsupervised machine learning (ML) prediction for target data, thus this will accelerate real world applications with ML models such as image recognition tasks in self-driving. Researchers have reported the UDA techniques are not working well under large co-variate shift problems where e.g. supervised source data consists of handwritten digits data in monotone color and unsupervised target data colored digits data from the street view. Thus there is a need for a method to resolve co-variate shift and transfer source labelling rules under this dynamics. We perform two stages domain invariant representation learning to bridge the gap between source and target with semantic intermediate data (unsupervised). The proposed method can learn domain invariant features simultaneously between source and intermediate also intermediate and target. Finally this achieves good domain invariant representation between source and target plus task discriminability owing to source labels. This induction for the gradient descent search greatly eases learning convergence in terms of classification performance for target data even when large co-variate shift. We also derive a theorem for measuring the gap between trained models and unsupervised target labelling rules, which is necessary for the free parameters optimization. Finally we demonstrate that proposing method is superiority to previous UDA methods using 4 representative ML classification datasets including 38 UDA tasks. Our experiment will be a basis for challenging UDA problems with large co-variate shift.

• Publication year

  2024

• Venue

  arXiv.org

• Publication date

  2024-12-06

• Fields of study

  Computer Science

• Identifiers
  DOI 10.48550/arXiv.2412.04682arXiv 2412.04682
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Inter-seasons and Inter-households Domain Adaptation Based on DANNs and Pseudo Labeling for Non-Intrusive Occupancy Detection

  2024influential reference
• AD-CLIP: Adapting Domains in Prompt Space Using CLIP

  2023cited by this paper
• Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? A Metric for Unsupervised Evaluation of Domain Adaptation

  2023cited by this paper
• Safe Self-Refinement for Transformer-based Domain Adaptation

  2022cited by this paper
• TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

  2021cited by this paper
• Semi-supervised domain generalization with evolving intermediate domain

  2021cited by this paper
• Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data

  2020cited by this paper
• On Learning Invariant Representations for Domain Adaptation

  2019influential reference
• Manifold Criterion Guided Transfer Learning via Intermediate Domain Generation

  2019cited by this paper
• Open Compound Domain Adaptation

  2019cited by this paper
• A survey on Image Data Augmentation for Deep Learning

  2019cited by this paper
• Time series feature learning with labeled and unlabeled data

  2019cited by this paper
• Aligning Infinite-Dimensional Covariance Matrices in Reproducing Kernel Hilbert Spaces for Domain Adaptation

  2018cited by this paper
• DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation

  2018cited by this paper
• Unsupervised Domain Adaptation by Mapped Correlation Alignment

  2018cited by this paper
• Characterizing and Avoiding Negative Transfer

  2018cited by this paper
• A Survey of Unsupervised Deep Domain Adaptation

  2018influential reference
• Self-ensembling for visual domain adaptation

  2017cited by this paper
• Deep Domain Adaptation by Geodesic Distance Minimization

  2017cited by this paper
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation

  2016influential reference
• Variational Recurrent Adversarial Deep Domain Adaptation

  2016cited by this paper
• Learning Transferable Features with Deep Adaptation Networks

  2015cited by this paper
• Smart Devices are Different: Assessing and MitigatingMobile Sensing Heterogeneities for Activity Recognition

  2015cited by this paper
• Active Learning for Multivariate Time Series Classification with Positive Unlabeled Data

  2015cited by this paper
• The ECO data set and the performance of non-intrusive load monitoring algorithms

  2014cited by this paper
• The Impact of Personalization on Smartphone-Based Activity Recognition

  2012cited by this paper
• Optimal kernel choice for large-scale two-sample tests

  2012cited by this paper
• Reading Digits in Natural Images with Unsupervised Feature Learning

  2011cited by this paper
• Enabling large-scale human activity inference on smartphones using community similarity networks (csn)

  2011cited by this paper
• Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning

  2010cited by this paper
• Visualizing Data using t-SNE

  2008cited by this paper
• Analysis of Representations for Domain Adaptation

  2006cited by this paper
• Validating clusters using the Hopkins statistic

  2004cited by this paper
• Gradient-based learning applied to document recognition

  1998cited by this paper

• No citing papers are available for this paper.