Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples. In this paper, we introduce an adaptive structure learning method to regularize the cooperation of SSL and DA. Inspired by the multi-views learning, our proposed framework is composed of a shared feature encoder network and two classifier networks, trained for contradictory purposes. Among them, one of the classifiers is applied to group target features to improve intra-class density, enlarging the gap of categorical clusters for robust representation learning. Meanwhile, the other classifier, serviced as a regularizer, attempts to scatter the source features to enhance the smoothness of the decision boundary. The iterations of target clustering and source expansion make the target features being well-enclosed inside the dilated boundary of the corresponding source points. For the joint address of cross-domain features alignment and partially labeled data learning, we apply the maximum mean discrepancy (MMD) distance minimization and self-training (ST) to project the contradictory structures into a shared view to make the reliable final decision. The experimental results over the standard SSDA benchmarks, including DomainNet and Office-home, demonstrate both the accuracy and robustness of our method over the state-of-the-art approaches.

翻译：半监督域适应(SSDA)是一个相当具有挑战性的问题,需要用多种方法克服以下两种问题:一是过于适应缺乏注释性的数据,二是跨域分布转移;不幸的是,由于对标签样本的培训数据偏向性,将域适应(DA)和半监督学习(SSL)方法简单组合在一起,往往无法解决这两个对象;在本文件中,我们采用了适应性结构学习方法,使SSL和DA的合作正规化;在多视角学习的启发下,我们提议的框架由共同的特征编码网络和两个分类网络组成,为相互矛盾的目的进行培训;其中,一个分类者用于群体目标特征,以提高类内密度,扩大绝对分组差距,以便进行有力的代表性学习;同时,其他分类者作为常规化者,试图分散源特性,以提高决定边界的顺利性;目标组合和源的扩展使得目标特征在相应源点的三角边界内被完全封闭;关于跨域特征的联合地址和部分标签性数据定位,包括S-D最终的精确性数据学习,我们把最起码的分类方法应用为S-D的自我测试标准。