王科,
闵子剑,
孙开伟,
邓欣
重庆邮电大学数据工程与可视计算重点实验室 ??重庆 ??400065
基金项目:国家自然科学基金(61806033), 国家社会科学基金西部项目(18XGL013)
详细信息
作者简介:王进:男,1979年生,教授,研究方向为机器学习、数据挖掘
王科:男,1993年生,硕士生,研究方向为机器学习
闵子剑:男,1995年生,硕士生,研究方向为机器学习
孙开伟:男,1987年生,讲师,研究方向为机器学习、数据挖掘
邓欣:男,1981年生,副教授,研究方向为机器学习、认知计算
通讯作者:王进 wangjin@cqupt.edu.cn
中图分类号:TP391.41计量
文章访问数:2329
HTML全文浏览量:1076
PDF下载量:61
被引次数:0
出版历程
收稿日期:2019-02-27
修回日期:2019-06-11
网络出版日期:2019-06-24
刊出日期:2019-11-01
Transfer Weight Based Conditional Adversarial Domain Adaptation
Jin WANG,,Ke WANG,
Zijian MIN,
Kaiwei SUN,
Xin DENG
Key Laboratory of Data Engineering and Visual Computing, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
Funds:The National Nature Science Foundation of China(61806033), The National Social Science Foundation of China(18XGL013)
摘要
摘要:针对条件对抗领域适应(CDAN)方法未能充分挖掘样本的可迁移性,仍然存在部分难以迁移的源域样本扰乱目标域数据分布的问题,该文提出一种基于迁移权重的条件对抗领域适应(TW-CDAN)方法。首先利用领域判别模型的判别结果作为衡量样本迁移性能的主要度量指标,使不同的样本具有不同的迁移性能;其次将样本的可迁移性作为权重应用在分类损失和最小熵损失上,旨在消除条件对抗领域适应中难以迁移样本对模型造成的影响;最后使用Office-31数据集的6个迁移任务和Office-Home数据集的12个迁移任务进行了实验,该方法在14个迁移任务上取得了提升,在平均精度上分别提升1.4%和3.1%。
关键词:迁移学习/
领域适应/
对抗学习/
迁移权重
Abstract:Considering the failure of the Conditional adversarial Domain AdaptatioN(CDAN) to fully utilize the sample transferability, which still struggle with some hard-to-transfer source samples disturbed the distribution of the target domain samples, a Transfer Weight based Conditional adversarial Domain AdaptatioN(TW-CDAN) is proposed. Firstly, the discriminant results in the domain discriminant model as the main factor are employed to measure the transfer performance. Then the weight is applied to class loss and minimum entropy loss. It is for eliminating the influence of hard-to-transfer samples of the model. Finally, experiments are carried out using the six domain adaptation tasks of the Office-31 dataset and the 12 domain adaptation tasks of the Office-Home dataset. The proposed method improves the 14 domain adaptation tasks and increases the average accuracy by 1.4% and 3.1% respectively.
Key words:Transfer learning/
Domain adaptation/
Adversarial learning/
Transfer Weight(TW)
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=d11313cd-73aa-4c3c-a151-f74c67632659