Unsupervised Domain Adaptation with Progressive Domain Augmentation
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.
References in corpus (13)
- Deep Visual Domain Adaptation: A Survey
- Conditional Adversarial Domain Adaptation
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- On Learning Invariant Representation for Domain Adaptation
- Efficient Learning of Domain-invariant Image Representations
- Co-regularized Alignment for Unsupervised Domain Adaptation
- Subspace Alignment For Domain Adaptation
- Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning
- Transfer Learning with Dynamic Adversarial Adaptation Network
- Domain Adaptations for Computer Vision Applications
- Correlation Alignment for Unsupervised Domain Adaptation
- Unsupervised Domain Adaptation with Random Walks on Target Labelings
- Domain Adaptation with Randomized Expectation Maximization