Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

Top Papers in Convolution

Share

Dynamic Convolution: Attention over Convolution Kernels

Light-weight convolutional neural networks (CNNs) suffer performance
degradation as their low computational budgets constrain both the depth (number
of convolution layers) and the width (number of cha

More...

Share

Dance Dance Convolution

Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players
perform steps on a dance platform in synchronization with music as directed by
on-screen step charts. While many step charts

More...

Share

Derivation and Analysis of Fast Bilinear Algorithms for Convolution

The prevalence of convolution in applications within signal processing, deep
neural networks, and numerical solvers has motivated the development of
numerous fast convolution algorithms. In many of th

More...

Share

Graph Homomorphism Convolution

In this paper, we study the graph classification problem from the graph
homomorphism perspective. We consider the homomorphisms from $F$ to $G$, where
$G$ is a graph of interest (e.g. molecules or soc

More...

Share

Counterpoint by Convolution

Machine learning models of music typically break up the task of composition
into a chronological process, composing a piece of music in a single pass from
beginning to end. On the contrary, human comp

More...

Share

Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize

The most prominent problem associated with the deconvolution layer is the
presence of checkerboard artifacts in output images and dense labels. To combat
this problem, smoothness constraints, post pro

More...

Share

ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision

Vision-and-Language Pretraining (VLP) has improved performance on various
joint vision-and-language downstream tasks. Current approaches for VLP heavily
rely on image feature extraction processes, mos

More...

Share

Fractional free convolution powers

The extension $k \mapsto \mu^{\boxplus k}$ of the concept of a free
convolution power to the case of non-integer $k \geq 1$ was introduced by
Bercovici-Voiculescu and Nica-Speicher, and related to the

More...

Share

Deformably-Scaled Transposed Convolution

Transposed convolution is crucial for generating high-resolution outputs, yet
has received little attention compared to convolution layers. In this work we
revisit transposed convolution and introduce

More...

Share

POCO: Point Convolution for Surface Reconstruction

Implicit neural networks have been successfully used for surface
reconstruction from point clouds. However, many of them face scalability issues
as they encode the isosurface function of a whole objec

More...

Share

Efficient Implementation of Multi-Channel Convolution in Monolithic 3D ReRAM Crossbar

Convolutional neural networks (CNNs) demonstrate promising accuracy in a wide
range of applications. Among all layers in CNNs, convolution layers are the
most computation-intensive and consume the mos

More...

Share

No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects

Convolutional neural networks (CNNs) have made resounding success in many
computer vision tasks such as image classification and object detection.
However, their performance degrades rapidly on toughe

More...

Share

D3Net: Densely connected multidilated DenseNet for music source separation

Music source separation involves a large input field to model a long-term
dependence of an audio signal. Previous convolutional neural network (CNN)
-based approaches address the large input field mod

More...

Share

Improving Neural Network Fault Tolerance with Winograd

Winograd Convolution: A Perspective from Fault Tolerance

Read More...

Share

Inception Convolution with Efficient Dilation Search

As a variant of standard convolution, a dilated convolution can control
effective receptive fields and handle large scale variance of objects without
introducing additional computational costs. To ful

More...

Share

Spatial Transformer Point Convolution

Point clouds are unstructured and unordered in the embedded 3D space. In
order to produce consistent responses under different permutation layouts, most
existing methods aggregate local spatial points

More...

Share

Generalized Multi-Relational Graph Convolution Network

Graph Convolutional Networks (GCNs) have received increasing attention in
recent machine learning. How to effectively leverage the rich structural
information in complex graphs, such as knowledge grap

More...

Share

LiteDepthwiseNet: An Extreme Lightweight Network for Hyperspectral Image Classification

Deep learning methods have shown considerable potential for hyperspectral
image (HSI) classification, which can achieve high accuracy compared with
traditional methods. However, they often need a larg

More...

Share

Diffusion Improves Graph Learning

Graph convolution is the core of most Graph Neural Networks (GNNs) and
usually approximated by message passing between direct (one-hop) neighbors. In
this work, we remove the restriction of using only

More...

Share

Focal Sparse Convolutional Networks for 3D Object Detection

Non-uniformed 3D sparse data, e.g., point clouds or voxels in different
spatial positions, make contribution to the task of 3D object detection in
different ways. Existing basic components in sparse c

More...

Share

More