Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation

Abstract

Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related but unlabeled data in a target domain. However, algorithm comparison is cumbersome in Deep UDA due to the absence of accurate and standardized model selection method, posing an obstacle to further advances in the field. Existing model selection methods for Deep UDA are either highly biased, restricted, unstable, or even controversial (requiring labeled target data). To this end, we propose \textit{Deep Embedded Validation} (\textbf{DEV}), which embeds adapted feature representation into the validation procedure to obtain unbiased estimation of the target risk with bounded variance. The variance is further reduced by the technique of control variate. The efficacy of the method has been justified both theoretically and empirically.

upload to arxiv for record

References in corpus (4)

• Conditional Adversarial Domain Adaptation
• Wasserstein Distance Guided Representation Learning for Domain Adaptation
• Detecting and Correcting for Label Shift with Black Box Predictors
• Regularized Learning for Domain Adaptation under Label Shifts

Cited by in corpus (24)

• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• Learning Causal Semantic Representation for Out-of-Distribution Prediction
• Minimum Class Confusion for Versatile Domain Adaptation
• Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation
• Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge
• Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
• Entropy Minimization vs. Diversity Maximization for Domain Adaptation
• Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
• Curriculum Manager for Source Selection in Multi-Source Domain Adaptation
• Semi-supervised on-device neural network adaptation for remote and portable laser-induced breakdown spectroscopy
• Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters
• Learning to Match Distributions for Domain Adaptation
• Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
• Unsupervised Calibration under Covariate Shift
• Moment-Based Domain Adaptation: Learning Bounds and Algorithms
• Featurized Density Ratio Estimation
• Energy-constrained Self-training for Unsupervised Domain Adaptation
• Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
• Information Theory-Guided Heuristic Progressive Multi-View Coding
• Dynamic Domain Adaptation for Efficient Inference
• Unsupervised Domain Adaptation: A Reality Check
• Transferable Semantic Augmentation for Domain Adaptation