论文标题
无监督领域适应的教师培训竞赛
Teacher-Student Competition for Unsupervised Domain Adaptation
论文作者
论文摘要
仅在源级别的源域的监督下，现有的无监督域适应（UDA）方法主要从共享的特征提取器中学习域 - 不变表示，这会导致源偏置问题。本文提出了一种无监督的域适应方法，即教师竞争（TSC）。特别是，引入了学生网络以学习针对目标特定的特征空间，我们设计了一种新颖的竞争机制，以选择更可靠的伪标签来培训学生网络。我们介绍了一个具有现有常规UDA方法的结构的教师网络，教师和学生网络都竞争提供目标伪标记，以限制每个目标样本在学生网络中的培训。广泛的实验表明，我们提出的TSC框架显着优于Office-31和ImageClef-DA基准的最新域适应方法。
With the supervision from source domain only in class-level, existing unsupervised domain adaptation (UDA) methods mainly learn the domain-invariant representations from a shared feature extractor, which causes the source-bias problem. This paper proposes an unsupervised domain adaptation approach with Teacher-Student Competition (TSC). In particular, a student network is introduced to learn the target-specific feature space, and we design a novel competition mechanism to select more credible pseudo-labels for the training of student network. We introduce a teacher network with the structure of existing conventional UDA method, and both teacher and student networks compete to provide target pseudo-labels to constrain every target sample's training in student network. Extensive experiments demonstrate that our proposed TSC framework significantly outperforms the state-of-the-art domain adaptation methods on Office-31 and ImageCLEF-DA benchmarks.
