Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning

by   Lei Tian, et al.

Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain. The key issue of domain adaptation is how to reduce the distribution discrepancy between two domains in a proper way such that they can be treated indifferently for learning. Different from existing methods that make label prediction for target samples independently, in this paper, we propose a novel domain adaptation approach that assigns pseudo-labels to target data with the guidance of class centroids in two domains, so that the data distribution structure of both source and target domains can be emphasized. Besides, to explore the structure information of target data more thoroughly, we further introduce a local connectivity self-learning strategy into our proposal to adaptively capture the inherent local manifold structure of target samples. The aforementioned class centroid matching and local manifold self-learning are integrated into one joint optimization problem and an iterative optimization algorithm is designed to solve it with theoretical convergence guarantee. In addition to unsupervised domain adaptation, we further extend our method to the semi-supervised scenario including both homogeneous and heterogeneous settings in a direct but elegant way. Extensive experiments on five benchmark datasets validate the significant superiority of our proposal in both unsupervised and semi-supervised manners.


page 4

page 5

page 6

page 7

page 9

page 10

page 12

page 13


Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning

Domain adaptation manages to transfer the knowledge of well-labeled sour...

Joint Information Preservation for Heterogeneous Domain Adaptation

Domain adaptation aims to assist the modeling tasks of the target domain...

Unsupervised Domain Adaptation via Discriminative Manifold Propagation

Unsupervised domain adaptation is effective in leveraging rich informati...

Gradual Domain Adaptation via Self-Training of Auxiliary Models

Domain adaptation becomes more challenging with increasing gaps between ...

Domain-shift adaptation via linear transformations

A predictor, f_A : X → Y, learned with data from a source domain (A) mig...

Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective

Endeavors have been recently made to leverage the vision transformer (Vi...

Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach

In unsupervised domain adaptation, it is widely known that the target do...

Please sign up or login with your details

Forgot password? Click here to reset