arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.03398cs.LGcs.CV
收藏

在$N$ D中实现通用的CNN远程并行计算

Towards a General Purpose CNN for Long Range Dependencies in $N$D

Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);University of Amsterdam(阿姆斯特丹大学);Stanford University(斯坦福大学)

David W. Romero, David M. Knigge, Albert Gu, Erik J. Bekkers, Efstratios Gavves, Jakub M. Tomczak, Mark Hoogendoorn

摘要:

卷积神经网络(CNN)的使用在深度学习中很广泛,因为它具有一系列理想的模型属性,这些属性可以产生高效和有效的机器学习框架。然而,高性能的CNN架构必须针对特定任务进行定制,以便纳入输入长度、分辨率和维度等考虑因素。在这项工作中,我们通过我们的连续卷积神经网络(CCNN)克服了对特定于问题的CNN架构的需求:一个配备连续卷积核的单一CNN架构,可用于任意分辨率,维度和长度的数据任务,而无需结构变化。连续卷积核在每一层都对长程依赖性进行建模,并消除了当前CNN架构中所需的下采样层和任务相关深度的需求。我们通过将相同的CCNN应用于顺序(1 $\mathrm{D}$)和视觉数据(2 $\mathrm{D}$)的广泛任务集来展示我们的方法的一般性。我们的CCNN具有竞争力,并且在所有考虑的任务中通常优于当前最先进的技术。

英文摘要:

The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework. However, performant CNN architectures must be tailored to specific tasks in order to incorporate considerations such as the input length, resolution, and dimentionality. In this work, we overcome the need for problem-specific CNN architectures with our Continuous Convolutional Neural Network (CCNN): a single CNN architecture equipped with continuous convolutional kernels that can be used for tasks on data of arbitrary resolution, dimensionality and length without structural changes. Continuous convolutional kernels model long range dependencies at every layer, and remove the need for downsampling layers and task-dependent depths needed in current CNN architectures. We show the generality of our approach by applying the same CCNN to a wide set of tasks on sequential (1$\mathrm{D}$) and visual data (2$\mathrm{D}$). Our CCNN performs competitively and often outperforms the current state-of-the-art across all tasks considered.

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。

↑