Hyper-Convolution Networks for Biomedical Image Segmentation

05/21/2021
by   Tianyu Ma, et al.
0

The convolution operation is a central building block of neural network architectures widely used in computer vision. The size of the convolution kernels determines both the expressiveness of convolutional neural networks (CNN), as well as the number of learnable parameters. Increasing the network capacity to capture rich pixel relationships requires increasing the number of learnable parameters, often leading to overfitting and/or lack of robustness. In this paper, we propose a powerful novel building block, the hyper-convolution, which implicitly represents the convolution kernel as a function of kernel coordinates. Hyper-convolutions enable decoupling the kernel size, and hence its receptive field, from the number of learnable parameters. In our experiments, focused on challenging biomedical image segmentation tasks, we demonstrate that replacing regular convolutions with hyper-convolutions leads to more efficient architectures that achieve improved accuracy. Our analysis also shows that learned hyper-convolutions are naturally regularized, which can offer better generalization performance. We believe that hyper-convolutions can be a powerful building block in future neural network architectures solving computer vision tasks.

READ FULL TEXT

page 4

page 8

research
02/06/2022

Hyper-Convolutions via Implicit Kernels for Medical Imaging

The convolutional neural network (CNN) is one of the most commonly used ...
research
11/01/2020

Convolution Neural Networks for Semantic Segmentation: Application to Small Datasets of Biomedical Images

This thesis studies how the segmentation results, produced by convolutio...
research
03/11/2019

HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs

We present a novel deep learning architecture in which the convolution o...
research
11/11/2018

Integrating Multiple Receptive Fields through Grouped Active Convolution

Convolutional networks have achieved great success in various vision tas...
research
03/19/2019

Efficient Smoothing of Dilated Convolutions for Image Segmentation

Dilated Convolutions have been shown to be highly useful for the task of...
research
04/10/2019

Pixel-Adaptive Convolutional Neural Networks

Convolutions are the fundamental building block of CNNs. The fact that t...
research
08/11/2019

ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

As designing appropriate Convolutional Neural Network (CNN) architecture...

Please sign up or login with your details

Forgot password? Click here to reset