Iterative Refinement for Multi-Source Visual Domain Adaptation

Hanrui Wu

doi:10.1109/TKDE.2020.3014697

Iterative Refinement for Multi-Source Visual Domain Adaptation

2021-01-01

27

PRE

AI

DOI：10.1109/TKDE.2020.3014697

原文链接

原文求助

摘要

En 中文

One of the main challenges in multi-source domain adaptation is how to reduce the domain discrepancy between each source domain and a target domain, and then evaluate the domain relevance to determine how much knowledge should be transferred from different source domains to the target domain. However, most prior approaches barely consider both discrepancies and relevance among domains. In this paper, we propose an algorithm, called Iterative Refinement based on Feature Selection and the Wasserstein distance (IRFSW), to solve semi-supervised domain adaptation with multiple sources. Specifically, IRFSW aims to explore both the discrepancies and relevance among domains in an iterative learning procedure, which gradually refines the learning performance until the algorithm stops. In each iteration, for each source domain and the target domain, we develop a sparse model to select features in which the domain discrepancy and training loss are reduced simultaneously. Then a classifier is constructed with the selected features of the source and labeled target data. After that, we exploit optimal transport over the selected features to calculate the transferred weights. The weight values are taken as the ensemble weights to combine the learned classifiers to control the amount of knowledge transferred from source domains to the target domain. Experimental results validate the effectiveness of the proposed method.

Keyword:

Iterative algorithms

Feature extraction

Training

Adaptation models

Support vector machines

Visualization

Data models

Domain adaptation

transfer learning

multiple sources

optimal transport

feature selection

Iterative Refinement for Multi-Source Visual Domain Adaptation

摘要

AI总结

期刊

机构