Abstract
Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN architectures. We present the Continuous Convolutional Neural Network (CCNN): a single CNN able to process data of arbitrary resolution, dimensionality and length without any structural changes. Its key component are its continuous convolutional kernels which model long-range dependencies at every layer, and thus remove the need of current CNN architectures for task-dependent downsampling and depths. We showcase the generality of our method by using the same architecture for tasks on sequential ($1{\rm D}$), visual ($2{\rm D}$) and point-cloud ($3{\rm D}$) data. Our CCNN matches and often outperforms the current state-of-the-art across all tasks considered.
Abstract (translated)
高效的卷积神经网络(CNN)架构必须针对特定的任务进行定制,以考虑输入数据的长度、分辨率和维度。在本文中,我们解决了需要特定任务CNN架构的问题。我们介绍了连续卷积神经网络(CCNN):一个单卷积神经网络,能够处理任意分辨率、维度和长度的数据,而不需要任何结构变化。其关键组件是其连续卷积核,在每个层中模型长距离依赖关系,从而消除了当前CNN架构中任务依赖的降采样和深度需求。我们通过使用相同的架构处理顺序(1D)、视觉(2D)和点云(3D)数据,展示了我们方法的通用性。我们的CCNN与当前最先进的技术非常相似,常常在各种任务中领先。
URL
https://arxiv.org/abs/2301.10540