Skip to yearly menu bar Skip to main content

In-Person Poster presentation / poster accept

Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN

David Knigge · David W. Romero · Albert Gu · Efstratios Gavves · Erik Bekkers · Jakub Tomczak · Mark Hoogendoorn · Jan-jakob Sonke

MH1-2-3-4 #45

Keywords: [ Deep Learning and representational learning ] [ sequential data ] [ continuous convolutional kernels ] [ visual data ] [ point-cloud data ] [ continuous parameterizations ] [ CNNs ] [ convolutional neural networks ]

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.

Chat is not available.