论文标题
通过新颖的阶级发现进行开放式域的适应
Open Set Domain Adaptation By Novel Class Discovery
论文作者
论文摘要
在开放式域适应（OSDA）中，大量目标样本来自从未出现在源域中的隐式类别。由于缺乏特定的归属，现有的方法不加区别地将其视为未知的单一类。我们挑战这种广泛的实践，可能会引起意外的有害影响，因为隐含类别之间的决策边界已被完全忽略。取而代之的是，我们提出了自我监督的类别 - 发现适配器（SCDA），该适配器（SCDA）试图通过逐渐发现那些隐式类来实现OSDA，然后将它们合并以重组分类器并迭代地更新域自动化功能。 SCDA分别执行了两个替代步骤，分别实现了隐式阶级发现和自我监督的OSDA。通过共同对两个任务进行优化，SCDA实现了OSDA的最先进，并显示出竞争性的表现，以发掘隐式目标类别。
In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specific belonging, existing methods indiscriminately regard them as a single class unknown. We challenge this broadly-adopted practice that may arouse unexpected detrimental effects because the decision boundaries between the implicit categories have been fully ignored. Instead, we propose Self-supervised Class-Discovering Adapter (SCDA) that attempts to achieve OSDA by gradually discovering those implicit classes, then incorporating them to restructure the classifier and update the domain-adaptive features iteratively. SCDA performs two alternate steps to achieve implicit class discovery and self-supervised OSDA, respectively. By jointly optimizing for two tasks, SCDA achieves the state-of-the-art in OSDA and shows a competitive performance to unearth the implicit target classes.
