This work provides a unified framework for addressing the problem of visual
supervised domain adaptation and generalization with deep models. The main idea
is to exploit the Siamese architecture to learn an embedding subspace that is
discriminative, and where mapped visual domains are semantically aligned and
yet maximally separated. The supervised setting becomes attractive especially
when only few target data samples need to be labeled. In this scenario,
alignment and separation of semantic probability distributions is difficult
because of the lack of data. We found that by reverting to point-wise
surrogates of distribution distances and similarities provides an effective
solution. In addition, the approach has a high speed of adaptation, which
requires an extremely low number of labeled target training samples, even one
per category can be effective. The approach is extended to domain
generalization. For both applications the experiments show very promising
results.

本文提出了一个视觉监督领域适应和泛化深度模型的统一框架，利用孪生网络结构来学习判别性嵌入子空间，通过点对代理的分布距离和相似性来解决少量目标数据样本标注的情况下，语义概率分布的对齐与分离问题。研究表明该方法在快速自适应方面的优势表现出来，并且只需要极少量的标注目标训练样本，甚至每个类别仅需一个标注样本就可以发挥有效性。此外，该方法还可扩展到领域泛化，并且实验证明该方法在两个应用领域都有很好的效果。