Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature discriminability. In this paper, we propose Discriminative Radial Domain Adaptation (DRDA) which bridges source and target domains via a shared radial structure. It's motivated by the observation that as the model is trained to be progressively discriminative, features of different categories expand outwards in different directions, forming a radial structure. We show that transferring such an inherently discriminative structure would enable to enhance feature transferability and discriminability simultaneously. Specifically, we represent each domain with a global anchor and each category a local anchor to form a radial structure and reduce domain shift via structure matching. It consists of two parts, namely isometric transformation to align the structure globally and local refinement to match each category. To enhance the discriminability of the structure, we further encourage samples to cluster close to the corresponding local anchors based on optimal-transport assignment. Extensively experimenting on multiple benchmarks, our method is shown to consistently outperforms state-of-the-art approaches on varied tasks, including the typical unsupervised domain adaptation, multi-source domain adaptation, domain-agnostic learning, and domain generalization.
翻译:域适应方法通过学习域- 差异性特征来减少域变。 多数现有方法都建立在分布匹配上, 例如对抗性域适应, 往往具有腐败性差异性。 在本文中, 我们提出通过共享的弧形结构连接源和目标域的偏差半域适应( DDRAD ) 。 它的动机是, 模型经过培训, 逐渐具有歧视性, 不同类别的特点在不同方向向外扩展, 形成一个辐射结构 。 我们表明, 转让这种固有的歧视性结构, 能够同时增强特征的可转移性和差异性。 具体地说, 我们代表每个领域, 以一个全球锚和每个类别代表一个本地锚, 形成一个辐射结构, 并通过结构匹配来减少域变换。 它由两部分组成, 即进行几度转换, 以协调全球结构和地方改进与每一类别相匹配。 为了加强结构的不均匀性, 我们进一步鼓励样本在最优化运输任务的基础上, 集中到相应的本地固定点。 在多个基准上进行广泛的实验, 我们的方法显示, 典型的域域域级外的适应, 包括不一域级化的多域化 。