论文标题
深度度量学习的球形特征变换
Spherical Feature Transform for Deep Metric Learning
论文作者
论文摘要
特征空间中的数据增强可有效增加数据多样性。以前的方法假设不同类别的特征分布具有相同的协方差。因此，通过翻译执行不同类别之间的特征变换。但是，这种方法不再对最近的深度度量学习方案有效，在该方案中，特征归一化被广泛采用，并且所有特征都位于超级球场上。 这项工作提出了一种新型的球形特征变换方法。它放松了类别之间相同的协方差的假设，即在超球场上不同类别的相似协方差的假设。因此，特征变换是通过尊重球形数据分布的旋转来执行的。我们提供了一种简单有效的训练方法，并在两种不同变换之间的关系中进行了深入的分析。关于各种深度度量学习基准和不同基线的全面实验证明了我们的方法是否可以提高性能和最先进的结果。
Data augmentation in feature space is effective to increase data diversity. Previous methods assume that different classes have the same covariance in their feature distributions. Thus, feature transform between different classes is performed via translation. However, this approach is no longer valid for recent deep metric learning scenarios, where feature normalization is widely adopted and all features lie on a hypersphere. This work proposes a novel spherical feature transform approach. It relaxes the assumption of identical covariance between classes to an assumption of similar covariances of different classes on a hypersphere. Consequently, the feature transform is performed by a rotation that respects the spherical data distributions. We provide a simple and effective training method, and in depth analysis on the relation between the two different transforms. Comprehensive experiments on various deep metric learning benchmarks and different baselines verify that our method achieves consistent performance improvement and state-of-the-art results.
