AI Chat AI Image Generator AI Video Text to Speech

GaborNet: Gabor filters with learnable parameters in deep convolutional neural networks

04/30/2019

∙

by Andrey Alekseev, et al.

∙

∙

The article describes a system for image recognition using deep convolutional neural networks. Modified network architecture is proposed that focuses on improving convergence and reducing training complexity. The filters in the first layer of the network are constrained to fit the Gabor function. The parameters of Gabor functions are learnable and are updated by standard backpropagation techniques. The system was implemented on Python, tested on several datasets and outperformed the common convolutional networks.

Andrey Alekseev
1 publication
Anatoly Bobe
1 publication

research

∙ 05/03/2017

Gabor Convolutional Networks

Steerable properties dominate the design of traditional filters, e.g., G...

0 Shangzhen Luan, et al. ∙

research

∙ 05/03/2015

ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks

In this paper, we propose a deep neural network architecture for object ...

0 Francesco Visin, et al. ∙

research

∙ 09/30/2015

Fast Algorithms for Convolutional Neural Networks

Deep convolutional neural networks take GPU days of compute time to trai...

0 Andrew Lavin, et al. ∙

research

∙ 02/28/2018

Convolutional Neural Networks with Alternately Updated Clique

Improving information flow in deep networks helps to ease the training d...

0 Yibo Yang, et al. ∙

research

∙ 04/25/2019

Optimal Approach for Image Recognition using Deep Convolutional Architecture

In the recent time deep learning has achieved huge popularity due to its...

0 Parth Shah, et al. ∙

research

∙ 02/02/2021

Orientation Convolutional Networks for Image Recognition

Deep Convolutional Neural Networks (DCNNs) are capable of obtaining powe...

0 Yalan Qin, et al. ∙

research

∙ 12/11/2019

Robust Gabor Networks

This work takes a step towards investigating the benefits of merging cla...

0 Juan C. Pérez, et al. ∙