Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the SSDA problem from two perspectives that have previously been overlooked, and correspondingly decompose it into two \emph{key subproblems}: \emph{robust domain adaptation (DA) learning} and \emph{maximal cross-domain data utilization}. \textbf{(i)} From a causal theoretical view, a robust DA model should distinguish the invariant ``concept'' (key clue to image label) from the nuisance of confounding factors across domains. To achieve this goal, we propose to generate \emph{concept-invariant samples} to enable the model to classify the samples through causal intervention, yielding improved generalization guarantees; \textbf{(ii)} Based on the robust DA theory, we aim to exploit the maximal utilization of rich source domain data and a few labeled target samples to boost SSDA further. Consequently, we propose a collaboratively debiasing learning framework that utilizes two complementary semi-supervised learning (SSL) classifiers to mutually exchange their unbiased knowledge, which helps unleash the potential of source and target domain training data, thereby producing more convincing pseudo-labels. Such obtained labels facilitate cross-domain feature alignment and duly improve the invariant concept learning. In our experimental study, we show that the proposed model significantly outperforms SOTA methods in terms of effectiveness and generalisability on SSDA datasets.
翻译:半监督域自适应领域中,我们既需要有效利用源域数据又需要仅仅使用少量的有标签目标样本。这是一种实用但鲜为人知的研究课题。本论文从两个被忽视的角度分析了半监督域自适应问题,据此将它分解成两种关键子问题:鲁棒性域自适应学习和最大化跨领域数据利用。第一,从因果理论的角度考虑,鲁棒性域适应模型必须区分横跨域之间的不变概念(图像标签的关键线索)和混淆因素的差异。为了实现这个目标,我们提出通过因果干预产生“概念不变抽样”来使模型具有分类样本的能力,从而得到改进后的泛化保证;第二,基于鲁棒性域适应理论,我们旨在充分利用丰富的源域数据和少量的有标目标样本以进一步提高半监督域自适应。因此,我们提出一个协同去偏策略学习框架,它利用两种互补的半监督学习分类器相互交换无偏知识,有助于释放源域和目标域训练数据的潜力,从而产生更为令人信服的伪标签。这些得到的标签有利于跨领域特征对齐,并且适当提高稳定的概念学习。通过实验,我们展示了所提出的模型在半监督域自适应数据集上在有效性和可泛化性方面显著优于现有最优解方法。