Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation
Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation
复制标题
DOI：
--
复制
发表时间：
2013-06
期刊：
影响因子：
--
通讯作者：
Boqing Gong;K. Grauman;Fei Sha
中科院分区：
文献类型：
--
作者：
Boqing Gong;K. Grauman;Fei Sha
学习域不变特征对于无监督域自适应至关重要，其中在源域上训练的分类器需要适应于没有标记示例的不同目标域。在本文中，我们提出了一种新的方法来学习这些功能。其中心思想是利用地标的存在，地标是源域中与目标域分布最相似的标记数据实例的子集。我们的方法自动发现的地标，并使用它们来构建可证明更容易的辅助域自适应任务的源目标。这些辅助任务的解决方案构成了为原始任务合成不变特征的基础。我们展示了这种组合物如何可以被优化的歧视，而不需要从目标域的标签。我们验证了标准的基准数据集的视觉对象识别和文本的情感分析的方法。实验结果表明，该方法优于国家的最先进的显着。
Learning domain-invariant features is of vital importance to unsupervised domain adaptation, where classifiers trained on the source domain need to be adapted to a different target domain for which no labeled examples are available. In this paper, we propose a novel approach for learning such features. The central idea is to exploit the existence of landmarks, which are a subset of labeled data instances in the source domain that are distributed most similarly to the target domain. Our approach automatically discovers the landmarks and use them to bridge the source to the target by constructing provably easier auxiliary domain adaptation tasks. The solutions of those auxiliary tasks form the basis to compose invariant features for the original task. We show how this composition can be optimized discriminatively without requiring labels from the target domain. We validate the method on standard benchmark datasets for visual object recognition and sentiment analysis of text. Empirical results show the proposed method outperforms the state-of-the-art significantly.