期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 30, 期 5, 页码 1381-1391出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2018.2868854
关键词
Dictionary learning; domain adaptation; feature representation; transfer learning
类别
资金
- National Natural Science Foundation of China [61371183, 61628206, 61806039]
- ARC [FT130101530]
- National Postdoctoral Program for Innovative Talents [BX201700045]
- China Postdoctoral Science Foundation [2017M623006]
- Applied Basic Research Program of Sichuan Province [2015JY0124]
In real-world transfer learning tasks, especially in cross-modal applications, the source domain and the target domain often have different features and distributions, which are well known as the heterogeneous domain adaptation (HDA) problem. Yet, existing HDA methods focus on either alleviating the feature discrepancy or mitigating the distribution divergence due to the challenges of HDA. In fact, optimizing one of them can reinforce the other. In this paper, we propose a novel HDA method that can optimize both feature discrepancy and distribution divergence in a unified objective function. Specifically, we present progressive alignment, which first learns a new transferable feature space by dictionary-sharing coding, and then aligns the distribution gaps on the new space. Different from previous HDA methods that are limited to specific scenarios, our approach can handle diverse features with arbitrary dimensions. Extensive experiments on various transfer learning tasks, such as image classification, text categorization, and text-to-image recognition, verify the superiority of our method against several state-of-the-art approaches.
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