论文标题
通过自我监督适应通用领域
Universal Domain Adaptation through Self Supervision
论文作者
论文摘要
传统上，无监督的域适应方法认为所有源类别都存在于目标域中。实际上，关于两个域之间的类别重叠的类别可能知之甚少。虽然某些方法以部分或开放集类别来解决目标设置，但他们假设特定设置已知先验。我们提出了一个更普遍适用的域自适应框架，该框架可以处理任意类别的偏移，称为域名通过熵优化（舞蹈）称为域适应性邻域聚类。舞蹈结合了两个新颖的想法：首先，由于我们不能完全依靠源类别来学习目标的特征，因此我们提出了一种新颖的邻里聚类技术，以一种自制的方式学习目标域的结构。其次，我们使用基于熵的特征对齐和拒绝将目标特征与源对齐，或者根据其熵拒绝它们作为未知类别。我们通过广泛的实验表明，舞蹈在开放式，开放式和部分领域的适应设置上超过了基线。实施可从https://github.com/visionlearninggroup/dance获得。
Unsupervised domain adaptation methods traditionally assume that all source categories are present in the target domain. In practice, little may be known about the category overlap between the two domains. While some methods address target settings with either partial or open-set categories, they assume that the particular setting is known a priori. We propose a more universally applicable domain adaptation framework that can handle arbitrary category shift, called Domain Adaptative Neighborhood Clustering via Entropy optimization (DANCE). DANCE combines two novel ideas: First, as we cannot fully rely on source categories to learn features discriminative for the target, we propose a novel neighborhood clustering technique to learn the structure of the target domain in a self-supervised way. Second, we use entropy-based feature alignment and rejection to align target features with the source, or reject them as unknown categories based on their entropy. We show through extensive experiments that DANCE outperforms baselines across open-set, open-partial and partial domain adaptation settings. Implementation is available at https://github.com/VisionLearningGroup/DANCE.
