期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 34, 期 11, 页码 8630-8641出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3151683
关键词
Adaptation models; Probability distribution; DNA; Neural networks; Kernel; Hilbert space; Data models; Domain adaptation; joint distribution matching; neural network; relative chi-square (RCS) divergence; reproducing kernel hilbert space (RKHS)
This article introduces a method called Domain Neural Adaptation (DNA) that uses nonlinear deep neural networks to solve the problem of domain adaptation. The method matches the joint distributions of the source and target domains and learns the classifier, resulting in a well-generalized classification model. Empirical results show that this method performs better than its competitors on several visual datasets.
Domain adaptation is concerned with the problem of generalizing a classification model to a target domain with little or no labeled data, by leveraging the abundant labeled data from a related source domain. The source and target domains possess different joint probability distributions, making it challenging for model generalization. In this article, we introduce domain neural adaptation (DNA): an approach that exploits nonlinear deep neural network to 1) match the source and target joint distributions in the network activation space and 2) learn the classifier in an end-to-end manner. Specifically, we employ the relative chi-square divergence to compare the two joint distributions, and show that the divergence can be estimated via seeking the maximal value of a quadratic functional over the reproducing kernel hilbert space. The analytic solution to this maximization problem enables us to explicitly express the divergence estimate as a function of the neural network mapping. We optimize the network parameters to minimize the estimated joint distribution divergence and the classification loss, yielding a classification model that generalizes well to the target domain. Empirical results on several visual datasets demonstrate that our solution is statistically better than its competitors.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据