论文标题
通用域适应的样本选择方法
A Sample Selection Approach for Universal Domain Adaptation
论文作者
论文摘要
我们研究了普遍场景中无监督域适应的问题，其中仅源和目标域之间仅共享某些类别。我们提出了一个有效识别共享类别样本的评分方案。该分数用于在训练过程中选择目标域中的哪些样品进行伪标记。另一个损失期限鼓励每批标签的多样性。综上所述，我们的方法表明，通过相当大的边距（文献基准上的最新技术状态）表现出胜过。
We study the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains. We present a scoring scheme that is effective in identifying the samples of the shared classes. The score is used to select which samples in the target domain to pseudo-label during training. Another loss term encourages diversity of labels within each batch. Taken together, our method is shown to outperform, by a sizable margin, the current state of the art on the literature benchmarks.
