Moment Matching for Multi-Source Domain Adaptation

Abstract

Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning approach, Moment Matching for Multi-Source Domain Adaptation M3SDA, which aims to transfer knowledge learned from multiple labeled source domains to an unlabeled target domain by dynamically aligning moments of their feature distributions. Third, we provide new theoretical insights specifically for moment matching approaches in both single and multiple source domain adaptation. Extensive experiments are conducted to demonstrate the power of our new dataset in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model. Dataset and Code are available at \url{http://ai.bu.edu/M3SDA/}.

arXiv commentAccepted As Oral Paper in the IEEE International Conference on Computer Vision 2019

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Domain Separation Networks
• VisDA: The Visual Domain Adaptation Challenge
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Generative Moment Matching Networks
• Algorithms and Theory for Multiple-Source Adaptation
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation

Cited by in corpus (19)

• Federated Adversarial Domain Adaptation
• Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
• Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies
• Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation
• Learning to Optimize Domain Specific Normalization for Domain Generalization
• MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge
• Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space
• Cross-domain few-shot learning with unlabelled data
• Curriculum Manager for Source Selection in Multi-Source Domain Adaptation
• On Universal Black-Box Domain Adaptation
• Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
• Domain-Adaptive Few-Shot Learning
• Domain Generalization via Semi-supervised Meta Learning
• Machine learning with limited data
• Learning Domain Adaptive Features with Unlabeled Domain Bridges
• Multi-source Domain Adaptation for Visual Sentiment Classification
• Domain Conditioned Adaptation Network
• Conceptual Expansion Neural Architecture Search (CENAS)
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition