基于迁移权重的条件对抗领域适应

Transfer Weight Based Conditional Adversarial Domain Adaptation

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%。

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(TWCDAN)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.