papers AI Learner
The Github is limit! Click to go to the new site.

Kervolutional Neural Networks

2019-04-08
Chen Wang, Jianfei Yang, Lihua Xie, Junsong Yuan

Abstract

Convolutional neural networks (CNNs) have enabled the state-of-the-art performance in many computer vision tasks. However, little effort has been devoted to establishing convolution in non-linear space. Existing works mainly leverage on the activation layers, which can only provide point-wise non-linearity. To solve this problem, a new operation, kervolution (kernel convolution), is introduced to approximate complex behaviors of human perception systems leveraging on the kernel trick. It generalizes convolution, enhances the model capacity, and captures higher order interactions of features, via patch-wise kernel functions, but without introducing additional parameters. Extensive experiments show that kervolutional neural networks (KNN) achieve higher accuracy and faster convergence than baseline CNN.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.03955

PDF

http://arxiv.org/pdf/1904.03955


Similar Posts

Comments