Correlation Alignment for Unsupervised Domain Adaptation
Correlation Alignment for Unsupervised Domain Adaptation
复制标题
DOI：
10.1007/978-3-319-58347-1_8
复制
发表时间：
2017-01-01
期刊：
影响因子：
--
通讯作者：
Saenko, Kate
中科院分区：
文献类型：
--
作者：
Sun, Baochen;Feng, Jiashi;Saenko, Kate
在本章中，我们提出了相关对齐（CORAL），一种简单而有效的无监督域自适应方法。CORAL通过对齐源和目标分布的二阶统计量来最大限度地减少域偏移，而不需要任何目标标签。与子空间流形方法相比，它对齐源域和目标域的原始特征分布，而不是低维子空间的基。它也比其他分布匹配方法简单得多。CORAL在标准基准数据集的广泛评估中表现出色。我们首先描述了一种解决方案，该解决方案对源特征应用线性变换，以在分类器训练之前将它们与目标特征对齐。对于线性分类器，我们建议等效地将CORAL应用于分类器权重，当分类器的数量很小时，但目标示例的数量和维度非常高时，可以提高效率。由此产生的CORAL线性判别分析（CORAL-LDA）优于LDA的标准域适应基准的大幅度提高。最后，我们扩展了CORAL来学习一种非线性变换，该变换可以调整深度神经网络（DNN）中层激活的相关性。由此产生的Deep CORAL方法与DNN无缝协作，并在标准基准数据集上实现了最先进的性能。我们的代码可在https://github.com/VisionLearningGroup/CORAL上获得。
In this chapter, we present CORrelation ALignment (CORAL), a simple yet effective method for unsupervised domain adaptation. CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. In contrast to subspace manifold methods, it aligns the original feature distributions of the source and target domains, rather than the bases of lower-dimensional subspaces. It is also much simpler than other distribution matching methods. CORAL performs remarkably well in extensive evaluations on standard benchmark datasets. We first describe a solution that applies a linear transformation to source features to align them with target features before classifier training. For linear classifiers, we propose to equivalently apply CORAL to the classifier weights, leading to added efficiency when the number of classifiers is small but the number and dimensionality of target examples are very high. The resulting CORAL Linear Discriminant Analysis (CORAL-LDA) outperforms LDA by a large margin on standard domain adaptation benchmarks. Finally, we extend CORAL to learn a nonlinear transformation that aligns correlations of layer activations in deep neural networks (DNNs). The resulting Deep CORAL approach works seamlessly with DNNs and achieves state-of-the-art performance on standard benchmark datasets. Our code is available at: https://github.com/VisionLearningGroup/CORAL.