Domain Separation Networks
Domain Separation Networks
复制标题
DOI：
--
复制
发表时间：
2016-08
期刊：
影响因子：
--
通讯作者：
Konstantinos Bousmalis;George Trigeorgis;N. Silberman;Dilip Krishnan;D. Erhan
中科院分区：
文献类型：
--
作者：
Konstantinos Bousmalis;George Trigeorgis;N. Silberman;Dilip Krishnan;D. Erhan
大规模数据收集和注释的成本往往使机器学习算法应用于新任务或数据集的成本过高。规避此成本的一种方法是在自动提供注释的合成数据上训练模型。尽管这些模型很有吸引力，但它们往往不能从合成图像推广到真实图像，因此需要领域自适应算法在成功应用之前对这些模型进行操作。现有的方法要么专注于将表示从一个领域映射到另一个领域，要么专注于学习提取对提取它们的领域不变的特征。然而，由于只关注在两个域之间创建映射或共享表示，它们忽略了每个域的单个特征。我们假设显式地对每个领域独特的东西进行建模可以提高模型提取领域不变特征的能力。受私有共享组件分析工作的启发，我们明确地学习提取分为两个子空间的图像表示：一个组件对每个域是私有的，另一个是跨域共享的。我们的模型被训练成不仅在源域中执行我们关心的任务，而且还使用分区表示从两个域中重构图像。我们的新架构产生了一个模型，在一系列无监督的领域适应场景中优于最先进的模型，并且还产生了私有和共享表示的可视化，从而能够解释领域适应过程。
The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data where annotations are provided automatically. Despite their appeal, such models often fail to generalize from synthetic to real images, necessitating domain adaptation algorithms to manipulate these models before they can be successfully applied. Existing approaches focus either on mapping representations from one domain to the other, or on learning to extract features that are invariant to the domain from which they were extracted. However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain. We hypothesize that explicitly modeling what is unique to each domain can improve a model's ability to extract domain-invariant features. Inspired by work on private-shared component analysis, we explicitly learn to extract image representations that are partitioned into two subspaces: one component which is private to each domain and one which is shared across domains. Our model is trained to not only perform the task we care about in the source domain, but also to use the partitioned representation to reconstruct the images from both domains. Our novel architecture results in a model that outperforms the state-of-the-art on a range of unsupervised domain adaptation scenarios and additionally produces visualizations of the private and shared representations enabling interpretation of the domain adaptation process.