当前位置: X-MOL 学术Int. J. Mach. Learn. & Cyber. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Learning discriminative feature via a generic auxiliary distribution for unsupervised domain adaptation
International Journal of Machine Learning and Cybernetics ( IF 3.1 ) Pub Date : 2021-07-23 , DOI: 10.1007/s13042-021-01381-x
Qipeng Chen 1 , Haofeng Zhang 1 , Qiaolin Ye 2 , Zheng Zhang 3 , Wankou Yang 4
Affiliation  

Traditional methods for unsupervised domain adaptation often leverage a projection matrix or a neural network as the feature extractor or classifier, where the feature extractor shared by the source and target domains enables the sample distributions to be aligned in the feature space, and simultaneously makes the source domain features separability enough for the classifier. However, only the alignment of both domains is not enough because the inter-class distance of some categories in the target domain may be too small, i.e., the feature separability is poor, which often leads to the bad condition that some samples are projected to the classification boundaries and thus misclassified. To solve this problem, we propose a pluggable generic auxiliary distribution (GAD) module for target domain in this paper. The proposed GAD module can iteratively refine the prediction of the target domain samples to increase the separability of the learned features, thereby increasing the distance between features of different categories. This operation can finally reduce the possibility of the target domain samples falling near the classification boundary, and leads to the improvement of classification accuracy for the target domain. Extensive experiments on several popular datasets are conducted, and the results demonstrate the effectiveness of the proposed method.



中文翻译:

通过无监督域适应的通用辅助分布学习判别特征

传统的无监督域自适应方法通常利用投影矩阵或神经网络作为特征提取器或分类器,其中源域和目标域共享的特征提取器使样本分布在特征空间中对齐,同时使源域域特征的可分性对于分类器来说足够了。然而,仅仅两个域的对齐是不够的,因为目标域中某些类别的类间距离可能太小,即特征可分性差,这往往导致某些样本被投影到的不良情况分类边界,从而错误分类。为了解决这个问题,我们在本文中提出了一个用于目标域的可插拔通用辅助分发(GAD)模块。提出的 GAD 模块可以迭代地细化目标域样本的预测,以增加学习到的特征的可分离性,从而增加不同类别特征之间的距离。该操作最终可以降低目标域样本落在分类边界附近的可能性,从而提高目标域的分类精度。对几个流行的数据集进行了大量实验,结果证明了所提出方法的有效性。并导致目标域分类精度的提高。对几个流行的数据集进行了大量实验,结果证明了所提出方法的有效性。并导致目标域分类精度的提高。对几个流行的数据集进行了大量实验,结果证明了所提出方法的有效性。

更新日期:2021-07-23
down
wechat
bug