Unsupervised Domain Adaptation with Progressive Domain Augmentation

2020/04/03 by Hua, Kevin, Guo, Yuhong
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2004.01735

Abstract

Domain adaptation aims to exploit a label-rich source domain for learning classifiers in a different label-scarce target domain. It is particularly challenging when there are significant divergences between the two domains. In the paper, we propose a novel unsupervised domain adaptation method based on progressive domain augmentation. The proposed method generates virtual intermediate domains via domain interpolation, progressively augments the source domain and bridges the source-target domain divergence by conducting multiple subspace alignment on the Grassmann manifold. We conduct experiments on multiple domain adaptation tasks and the results shows the proposed method achieves the state-of-the-art performance.

Related

• Progressive Feature Alignment for Unsupervised Domain Adaptation
• Unsupervised Domain Adaptation: A Multi-task Learning-based Method
• Unsupervised Domain Adaptation via Discriminative Manifold Embedding and Alignment
• Gradual Domain Adaptation: Theory and Algorithms
• Cross-domain error minimization for unsupervised domain adaptation