Unsupervised domain adaptation (UDA) serves to transfer specific knowledge from massive labeled source domain data to unlabeled target domain data via mitigating domain shift. In this paper, we propose a discriminative relevance regularization term (DRR) to enhance the performance of UDA by reducing the domain shift from the aspect of semantic relevance across domains. In particular, DRR is formulated as the min–max rank problem which seeks a projection matrix to minimize the rank of intra-class projected features and maximize the rank of the means of inter-class projected features simultaneously. To test the potential effectiveness of DRR, we design a relevance regularized distribution adaptation method (RRDA) and relevance regularized adaptation networks (RRAN) for image classification, and a relevance regularized self-supervised learning method (RRSL) for semantic segmentation by incorporation of DRR. The corresponding optimization algorithms are proposed to solve them. Experiments of cross-domain image classification show that both RRDA and RRAN outperform several state-of-the-art compared methods. Moreover, experiments of domain-adaptation semantic segmentation on two synthetic-to-real segmentation datasets demonstrate the capacity of RRSL. Such results imply the efficacy of DRR on both image classification and semantic segmentation tasks.

中文翻译：

---

通过区分性相关正则化增强无监督域自适应

无监督域自适应（UDA）用于通过减轻域偏移将特定知识从大量标记的源域数据转移到未标记的目标域数据。在本文中，我们提出了区分性关联正则化术语（DRR），以从跨域语义相关性的角度减少域移位，从而提高UDA的性能。特别地，DRR被公式化为最小-最大等级问题，该问题寻求投影矩阵以最小化类内投影特征的等级并同时最大化类间投影特征的均值的等级。为了测试DRR的潜在效果，我们针对图像分类设计了相关正则分布自适应方法（RRDA）和相关正则自适应网络（RRAN），以及通过结合DRR进行语义分割的相关正则化自我监督学习方法（RRSL）。提出了相应的优化算法对其进行求解。跨域图像分类的实验表明，RRDA和RRAN均优于几种最先进的比较方法。此外，在两个合成到真实的分割数据集上进行域自适应语义分割的实验证明了RRSL的能力。这样的结果暗示了DRR在图像分类和语义分割任务上的功效。在两个从合成到真实的分割数据集上进行域自适应语义分割的实验证明了RRSL的能力。这样的结果暗示了DRR在图像分类和语义分割任务上的功效。在两个从合成到真实的分割数据集上进行域自适应语义分割的实验证明了RRSL的能力。这样的结果暗示了DRR在图像分类和语义分割任务上的功效。