While researchers continue to find new and improved network structures for CNNs, most of the newly invented architectures still rely on the traditional pattern of stacking convolutional blocks and separating them with pointwise activation functions. However, there are drawbacks to a network purely building on pointwise nonlinearities. One alternative is to introduce a pairwise connection between two filters of a network. Typical connection functions use multiplications or the minimum operation to realize logical AND connections. In this paper, we go one step further by demonstrating that CNNs can benefit from more general connections, which include parameters that are learned. With such parameters, the network is able to implement different connections in different network layers and better adapt the connection function to the task at hand.

翻译：尽管研究人员不断为卷积神经网络（CNN）寻找新颖且改进的网络结构，但多数新发明架构仍依赖传统模式——堆叠卷积模块并以逐点激活函数分隔。然而，纯粹基于逐点非线性构建的网络存在缺陷。一种替代方案是在网络的两滤波器间引入成对连接。典型连接函数通过乘法或最小值运算实现逻辑与连接。本文更进一步，证明CNN可从更通用的连接中受益——这类连接包含可学习参数。借助此类参数，网络能在不同网络层实现差异化连接，使连接函数更适应目标任务。