Improve Unsupervised Domain Adaptation with Mixup Training

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.

References in corpus (4)

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

Cited by in corpus (23)

• In Search of Lost Domain Generalization
• Domain Generalization using Causal Matching
• Towards a Theoretical Framework of Out-of-Distribution Generalization
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• Inter-Domain Mixup for Semi-Supervised Domain Adaptation
• Rethinking Domain Generalization: Discriminability and Generalizability
• Nonlinear Invariant Risk Minimization: A Causal Approach
• SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
• Universum-inspired Supervised Contrastive Learning
• Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
• Gradient Matching for Domain Generalization
• Out-of-Distribution Generalization Analysis via Influence Function
• Adaptive Domain Generalization via Online Disagreement Minimization
• Model-Based Domain Generalization
• Accounting for Unobserved Confounding in Domain Generalization
• Quantifying and Improving Transferability in Domain Generalization
• A Fine-Grained Analysis on Distribution Shift
• SWAD: Domain Generalization by Seeking Flat Minima
• CNN Feature Map Augmentation for Single-Source Domain Generalization
• Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
• Explainability-aided Domain Generalization for Image Classification
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection
• Towards Data-Free Domain Generalization