Improve Unsupervised Domain Adaptation with Mixup Training

2020/01/03 by Shen Yan, Yan, Shen, Huan Song +8 · 16 citations
Computer Science · Mathematics · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Neonatal and fetal brain pathology #cs.CV #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2001.00677

arxiv created 2020/01/03 · openalex publication_date 2020/01/03 · arxiv updated 2020/01/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of learning domain-invariant features is insufficient to achieve desirable target domain performance and thus introduce additional training constraints, e.g. cluster assumption. However, these approaches impose the constraints on source and target domains individually, ignoring the important interplay between them. In this work, we propose to enforce training constraints across domains using mixup formulation to directly address the generalization performance for target data. In order to tackle potentially huge domain discrepancy, we further propose a feature-level consistency regularizer to facilitate the inter-domain constraint. When adding intra-domain mixup and domain adversarial learning, our general framework significantly improves state-of-the-art performance on several important tasks from both image classification and human activity recognition.

Citations

• Asymmetric Tri-training for Unsupervised Domain Adaptation
• mixup: Beyond Empirical Risk Minimization
• Conditional Adversarial Domain Adaptation
• MixMatch: A Holistic Approach to Semi-Supervised Learning

Cited by

• Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners
• D-GAP: Improving Out-of-Domain Robustness via Dataset-Agnostic and Gradient-Guided Augmentation in Amplitude and Pixel Spaces
• Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
• Exploring Scale Shift in Crowd Localization under the Context of Domain Generalization
• High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
• Single Domain Generalization in Diabetic Retinopathy: A Neuro-Symbolic Learning Approach
• Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains
• Domain Generalization via Pareto Optimal Gradient Matching
• Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization
• Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization
• Towards a Theoretical Framework of Out-of-Distribution Generalization
• Towards Data-Free Domain Generalization
• Pseudo Multi-Source Domain Generalization: Bridging the Gap Between Single and Multi-Source Domain Generalization
• When Shift Happens - Confounding Is to Blame
• Improving Out-of-Domain Robustness with Targeted Augmentation in Frequency and Pixel Spaces
• Continuous Domain Generalization
• Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucination

Related

• Dual Mixup Regularized Learning for Adversarial Domain Adaptation
• Adversarial Domain Adaptation with Domain Mixup
• Self-Supervised Domain Adaptation with Consistency Training
• FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
• FIXED: Frustratingly Easy Domain Generalization with Mixup