计算机工程与应用2019，Vol.55Issue(14)：24-31,8.DOI:10.3778/j.issn.1002-8331.1903-0430
最小二乘迁移生成对抗网络
Least Squares Transfer Generative Adversarial Networks
摘要
Abstract
The existing Generative Adversarial Networks(GAN)loss function has been successfully used in transfer learning method. However, it is found that this loss function may lead to the vanishing gradients problem during the learn-ing process. To overcome this problem, a new learning domain invariant feature approach, Least Squares Transfer Genera-tive Adversarial Networks(LSTGAN), is proposed. LSTGAN adopts least squares generative adversarial networks loss function to reduce the discrepancy of domain distribution by a single-domain discrimination training way. The research shows that the proposed method has certain advantages compared with other competitive algorithms.关键词
生成对抗网络/迁移学习/梯度消失/领域不变特征/最小二乘生成对抗网络损失函数Key words
generative adversarial networks/transfer learning/vanishing gradients/domain invariant feature/least squares generative adversarial networks loss function分类
信息技术与安全科学引用本文复制引用
王孝顺,陈丹,丘海斌..最小二乘迁移生成对抗网络[J].计算机工程与应用,2019,55(14):24-31,8.基金项目
福建省自然科学基金(No.2018J01534). （No.2018J01534）
