Joint Information Preservation for Heterogeneous Domain Adaptation

05/22/2019
by   Peng Xu, et al.
1

Domain adaptation aims to assist the modeling tasks of the target domain with knowledge of the source domain. The two domains often lie in different feature spaces due to diverse data collection methods, which leads to the more challenging task of heterogeneous domain adaptation (HDA). A core issue of HDA is how to preserve the information of the original data during adaptation. In this paper, we propose a joint information preservation method to deal with the problem. The method preserves the information of the original data from two aspects. On the one hand, although paired samples often exist between the two domains of the HDA, current algorithms do not utilize such information sufficiently. The proposed method preserves the paired information by maximizing the correlation of the paired samples in the shared subspace. On the other hand, the proposed method improves the strategy of preserving the structural information of the original data, where the local and global structural information are preserved simultaneously. Finally, the joint information preservation is integrated by distribution matching. Experimental results show the superiority of the proposed method over the state-of-the-art HDA algorithms.

READ FULL TEXT
research
03/20/2020

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

Domain adaptation has been a fundamental technology for transferring kno...
research
04/26/2020

Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation

Heterogeneous Domain Adaptation (HDA) aims to enable effective transfer ...
research
08/16/2019

Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning

Supervised learning algorithms trained on medical images will often fail...
research
09/07/2021

Grassmannian Graph-attentional Landmark Selection for Domain Adaptation

Domain adaptation aims to leverage information from the source domain to...
research
07/04/2023

AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation

Few-shot image generation (FSIG) aims to learn to generate new and diver...
research
07/08/2019

Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching

A broad range of cross-m-domain generation researches boil down to match...
research
01/17/2020

Preservation of Equations by Monoidal Monads

If a monad T is monoidal, then operations on a set X can be lifted canon...

Please sign up or login with your details

Forgot password? Click here to reset