A review of domain adaptation without target labels

Abstract

Domain adaptation has become a prominent problem setting in machine learning and related fields. This review asks the question: how can a classifier learn from a source domain and generalize to a target domain? We present a categorization of approaches, divided into, what we refer to as, sample-based, feature-based and inference-based methods. Sample-based methods focus on weighting individual observations during training based on their importance to the target domain. Feature-based methods revolve around on mapping, projecting and representing features such that a source classifier performs well on the target domain and inference-based methods incorporate adaptation into the parameter estimation procedure, for instance through constraints on the optimization procedure. Additionally, we review a number of conditions that allow for formulating bounds on the cross-domain generalization error. Our categorization highlights recurring ideas and raises questions important to further research.

20 pages, 5 figures

References in corpus (15)

• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Equality of Opportunity in Supervised Learning
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Separation Networks
• Domain Generalization via Invariant Feature Representation
• Marginalized Denoising Autoencoders for Domain Adaptation
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation
• Multiple Source Adaptation and the Renyi Divergence
• Regularized Learning for Domain Adaptation under Label Shifts
• Analysis of Kernel Mean Matching under Covariate Shift
• A cross-center smoothness prior for variational Bayesian brain tissue segmentation
• Learning an MR acquisition-invariant representation using Siamese neural networks
• On Deep Domain Adaptation: Some Theoretical Understandings

Cited by in corpus (55)

• Domain Adaptation for Medical Image Analysis: A Survey
• Maximum Density Divergence for Domain Adaptation
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology
• Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
• Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
• On The Effects Of Data Normalisation For Domain Adaptation On EEG Data
• Learning Transferable Parameters for Unsupervised Domain Adaptation
• Automated Extraction of Energy Systems Information from Remotely Sensed Data: A Review and Analysis
• Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces
• Domain Adaptation for Robust Workload Level Alignment Between Sessions and Subjects using fNIRS
• Federated Domain Generalization: A Survey
• The Data Representativeness Criterion: Predicting the Performance of Supervised Classification Based on Data Set Similarity
• Learning causal representations for robust domain adaptation
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error
• Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey
• Saliency is a Possible Red Herring When Diagnosing Poor Generalization
• Deep Domain Adaptive Object Detection: a Survey
• A cross-center smoothness prior for variational Bayesian brain tissue segmentation
• EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking
• Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
• Generalizable deep learning for photoplethysmography-based blood pressure estimation -- A Benchmarking Study
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Time Series Alignment with Global Invariances
• Reducing Annotating Load: Active Learning with Synthetic Images in Surgical Instrument Segmentation
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• Respecting Domain Relations: Hypothesis Invariance for Domain Generalization
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Sample Selection Bias in Machine Learning for Healthcare
• The Little W-Net That Could: State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models
• Stratified Learning: A General-Purpose Statistical Method for Improved Learning under Covariate Shift
• Machine Learning-Augmented Optimization of Large Bilevel and Two-stage Stochastic Programs: Application to Cycling Network Design
• Unsupervised Calibration under Covariate Shift
• A hybrid model-based and learning-based approach for classification using limited number of training samples
• Modelling of Networked Measuring Systems -- From White-Box Models to Data Based Approaches
• LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives
• Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources
• Invariant Feature Learning for Sensor-based Human Activity Recognition
• Incremental Unsupervised Domain-Adversarial Training of Neural Networks
• Back to the Future -- Sequential Alignment of Text Representations
• Out-of-Distribution Generalization in Kernel Regression
• Towards to Robust and Generalized Medical Image Segmentation Framework
• Domain Adaptation in Highly Imbalanced and Overlapping Datasets
• Semi-Supervised Adversarial Discriminative Domain Adaptation
• Teacher-Student Consistency For Multi-Source Domain Adaptation
• Comorbidity-Informed Transfer Learning for Neuro-developmental Disorder Diagnosis
• Self-Labeling of Fully Mediating Representations by Graph Alignment
• Generic Semi-Supervised Adversarial Subject Translation for Sensor-Based Human Activity Recognition
• A Batch Normalization Classifier for Domain Adaptation
• fMBN-E: Efficient Unsupervised Network Structure Ensemble and Selection for Clustering
• Towards Explainable Fact Checking
• Knothe-Rosenblatt transport for Unsupervised Domain Adaptation
• Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance
• Factorizable joint shift revisited