Open-set domain adaptation (OSDA) considers that the target domain contains samples from novel categories unobserved in external source domain. Unfortunately, existing OSDA methods always ignore the demand for the information of unseen categories and simply recognize them as "unknown" set without further explanation. This motivates us to understand the unknown categories more specifically by exploring the underlying structures and recovering their interpretable semantic attributes. In this paper, we propose a novel framework to accurately identify the seen categories in target domain, and effectively recover the semantic attributes for unseen categories. Specifically, structure preserving partial alignment is developed to recognize the seen categories through domain-invariant feature learning. Attribute propagation over visual graph is designed to smoothly transit attributes from seen to unseen categories via visual-semantic mapping. Moreover, two new cross-main benchmarks are constructed to evaluate the proposed framework in the novel and practical challenge. Experimental results on open-set recognition and semantic recovery demonstrate the superiority of the proposed method over other compared baselines.
翻译:开放域适应( OSDA) 认为目标域包含外部源域未观测到的新类别样本。 不幸的是, 现有的 OSDA 方法总是忽视对不可见类别信息的需求, 简单地承认它们为“ 未知的” 类别, 而没有进一步解释。 这促使我们更具体地理解未知类别, 探索基础结构并恢复其可解释的语义属性。 在本文中, 我们提出了一个新框架, 以准确识别目标域的可见类别, 并有效恢复不可见类别的语义属性。 具体地说, 保留部分对齐的结构是用来通过域- 异性特征学习来识别所见类别的结构。 视觉图的属性传播旨在通过视觉- 语义绘图将所见的属性顺利地从可见类别转换为不可见类别。 此外, 还建立了两个新的跨界基准, 以评价新颖和实用的挑战中的拟议框架。 开放式识别和语义恢复的实验结果显示了拟议方法优于其他基线。