DEFRAG:通过格拉斯曼流形上的自适应实现的深度欧几里德特征表示
DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold
摘要:
我们提出了一种训练深度网络的新技术,其目标是获得存在于欧几里得空间中并表现出强聚类行为的特征表示。我们所期望的特征表示有三个特点:它们可以使用标准的欧几里得距离度量进行比较,来自同一类的样本紧密聚类,来自不同类的样本分离良好。然而,大多数深度网络并不强制执行这样的特征表示。DEFRAG训练技术包括两个步骤:首先,通过基于Silhouette聚类度量的辅助损失函数来鼓励良好的特征聚类行为。然后将特征空间收缩到Grassmann流形上,以保证L_2范数形成相似性度量。DEFRAG技术在标准分类数据集上实现了最先进的结果,使用相对较小的网络架构,参数明显少于许多标准网络。
英文摘要:
We propose a novel technique for training deep networks with the objective of obtaining feature representations that exist in a Euclidean space and exhibit strong clustering behavior. Our desired features representations have three traits: they can be compared using a standard Euclidian distance metric, samples from the same class are tightly clustered, and samples from different classes are well separated. However, most deep networks do not enforce such feature representations. The DEFRAG training technique consists of two steps: first good feature clustering behavior is encouraged though an auxiliary loss function based on the Silhouette clustering metric. Then the feature space is retracted onto a Grassmann manifold to ensure that the L_2 Norm forms a similarity metric. The DEFRAG technique achieves state of the art results on standard classification datasets using a relatively small network architecture with significantly fewer parameters than many standard networks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。