关于卷积神经网络不适用于非局部任务的论证
Arguments for the Unsuitability of Convolutional Neural Networks for Non--Local Tasks
摘要：
卷积神经网络在过去几年中已经确立了自己作为图像分类的最先进方法的地位，对于许多数据集，它们甚至在分类图像方面超过了人类。不幸的是，相同的架构在必须将图像的部分相互比较以正确分类该图像时表现得更差。到目前为止，还没有形成良好的理论论据来解释这一缺陷。在本文中，我们将认为卷积层对此类问题几乎没有用处，因为比较任务本质上是全局的，但卷积层在设计上是局部的。我们将利用这一洞察力将比较任务重新定义为排序任务，并利用排序网络的发现提出一个神经网络以可推广的方式解决比较任务所需参数数量的下限。我们将使用这个下限来论证注意力以及迭代/递归处理是防止组合爆炸所必需的。
英文摘要：
Convolutional neural networks have established themselves over the past years as the state of the art method for image classification, and for many datasets, they even surpass humans in categorizing images. Unfortunately, the same architectures perform much worse when they have to compare parts of an image to each other to correctly classify this image. Until now, no well-formed theoretical argument has been presented to explain this deficiency. In this paper, we will argue that convolutional layers are of little use for such problems, since comparison tasks are global by nature, but convolutional layers are local by design. We will use this insight to reformulate a comparison task into a sorting task and use findings on sorting networks to propose a lower bound for the number of parameters a neural network needs to solve comparison tasks in a generalizable way. We will use this lower bound to argue that attention, as well as iterative/recurrent processing, is needed to prevent a combinatorial explosion.
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。
