arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.09307cs.LGstat.ML
收藏

利用类别信息进行深度网络表示整形

Utilizing Class Information for Deep Network Representation Shaping

Seoul National University(首尔国立大学)

Daeyoung Choi, Wonjong Rhee

摘要:

深度网络表示的统计特征,例如稀疏性和相关性,已知与深度学习的性能和可解释性相关。当需要统计特性时,通常可以在训练阶段设计和应用适当的正则化器。通常,这样的正则化器旨在一起操纵所有类的统计特征。然而,对于分类任务,可能有利的是强制每个类别的期望特征,使得可以更好地区分不同的类别。基于这个想法,我们设计了两个明确利用类信息的类正则化器:类协方差正则化器(cw-CR)和类方差正则化器(cw-VR)。cw-CR的目标是减少从同一类样本计算的表示的协方差,以鼓励特征独立性。cw-VR是类似的,但方差而不是协方差的目标是提高特征紧凑性。为了完整起见,它们的对应物,不使用类信息,协方差正则化(CR)和方差正则化(VR),被认为是在一起。这四个正则化器在概念上很简单,计算效率也很高,可视化显示正则化器确实执行了不同的表示整形。在分类性能方面,在流行的基准数据集上,22个任务中有21个任务比基线和L1/L2权重正则化方法有显着改进。特别是,cw-VR在包括ResNet-32/110在内的13项任务中取得了最佳性能。

英文摘要:

Statistical characteristics of deep network representations, such as sparsity and correlation, are known to be relevant to the performance and interpretability of deep learning. When a statistical characteristic is desired, often an adequate regularizer can be designed and applied during the training phase. Typically, such a regularizer aims to manipulate a statistical characteristic over all classes together. For classification tasks, however, it might be advantageous to enforce the desired characteristic per class such that different classes can be better distinguished. Motivated by the idea, we design two class-wise regularizers that explicitly utilize class information: class-wise Covariance Regularizer (cw-CR) and class-wise Variance Regularizer (cw-VR). cw-CR targets to reduce the covariance of representations calculated from the same class samples for encouraging feature independence. cw-VR is similar, but variance instead of covariance is targeted to improve feature compactness. For the sake of completeness, their counterparts without using class information, Covariance Regularizer (CR) and Variance Regularizer (VR), are considered together. The four regularizers are conceptually simple and computationally very efficient, and the visualization shows that the regularizers indeed perform distinct representation shaping. In terms of classification performance, significant improvements over the baseline and L1/L2 weight regularization methods were found for 21 out of 22 tasks over popular benchmark datasets. In particular, cw-VR achieved the best performance for 13 tasks including ResNet-32/110.

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。

↑