arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.15459cs.CV
收藏

Capsule网络并不比卷积网络更健壮

Capsule Network is Not More Robust than Convolutional Network

University of Munich(慕尼黑大学);Microsoft Research Asia(微软亚洲研究院)

Jindong Gu, Volker Tresp, Han Hu

摘要:

胶囊网络被广泛认为比卷积网络更强大。然而,这两个网络之间没有全面的比较,也不知道CapsNet中的哪些组件会影响其鲁棒性。在本文中,我们首先仔细研究了CapsNet中与通常用于图像分类的ConvNet不同的特殊设计。该研究揭示了CapsNet中五个主要的新的/不同的组件:转换过程,动态路由层,挤压函数,除了交叉熵损失之外的边际损失,以及用于正则化的额外类条件重建损失。除了这些主要的差异,我们对三种鲁棒性进行了全面的消融研究,包括仿射变换,重叠数字和语义表示。该研究表明,一些被认为对CapsNet至关重要的设计实际上会损害其鲁棒性,即,动态路由层和转换过程,而其他则有利于鲁棒性。基于这些发现,我们提出了增强的ConvNets,只需引入CapsNet成功背后的基本组件。所提出的简单ConvNets可以实现比CapsNet更好的鲁棒性。

英文摘要:

The Capsule Network is widely believed to be more robust than Convolutional Networks. However, there are no comprehensive comparisons between these two networks, and it is also unknown which components in the CapsNet affect its robustness. In this paper, we first carefully examine the special designs in CapsNet that differ from that of a ConvNet commonly used for image classification. The examination reveals five major new/different components in CapsNet: a transformation process, a dynamic routing layer, a squashing function, a marginal loss other than cross-entropy loss, and an additional class-conditional reconstruction loss for regularization. Along with these major differences, we conduct comprehensive ablation studies on three kinds of robustness, including affine transformation, overlapping digits, and semantic representation. The study reveals that some designs, which are thought critical to CapsNet, actually can harm its robustness, i.e., the dynamic routing layer and the transformation process, while others are beneficial for the robustness. Based on these findings, we propose enhanced ConvNets simply by introducing the essential components behind the CapsNet's success. The proposed simple ConvNets can achieve better robustness than the CapsNet.

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。

↑