Connections Between Pairs of Filters Improve the Accuracy of Convolutional Neural Networks

Abstract

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.
Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks (IJCNN)
Number of pages7
PublisherIEEE
Publication date18.06.2023
Pages1-7
ISBN (Print)978-1-6654-8868-6
ISBN (Electronic)978-1-6654-8867-9
DOIs
Publication statusPublished - 18.06.2023

Cite this