Filter Distribution Templates in Convolutional Networks for Image Classification Tasks

04/28/2021
by   Ramon Izquierdo-Cordova, et al.
0

Neural network designers have reached progressive accuracy by increasing models depth, introducing new layer types and discovering new combinations of layers. A common element in many architectures is the distribution of the number of filters in each layer. Neural network models keep a pattern design of increasing filters in deeper layers such as those in LeNet, VGG, ResNet, MobileNet and even in automatic discovered architectures such as NASNet. It remains unknown if this pyramidal distribution of filters is the best for different tasks and constrains. In this work we present a series of modifications in the distribution of filters in four popular neural network models and their effects in accuracy and resource consumption. Results show that by applying this approach, some models improve up to 8.9 showing reductions in parameters up to 54

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/17/2021

Towards Efficient Convolutional Network Models with Filter Distribution Templates

Increasing number of filters in deeper layers when feature maps are decr...
research
01/28/2019

Convolutional Neural Networks with Layer Reuse

A convolutional layer in a Convolutional Neural Network (CNN) consists o...
research
12/14/2018

Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

We characterize convolutional neural networks with respect to the relati...
research
06/02/2020

Studying The Effect of MIL Pooling Filters on MIL Tasks

There are different multiple instance learning (MIL) pooling filters use...
research
11/30/2020

Why Convolutional Networks Learn Oriented Bandpass Filters: Theory and Empirical Support

It has been repeatedly observed that convolutional architectures when ap...
research
12/11/2019

Robust Gabor Networks

This work takes a step towards investigating the benefits of merging cla...
research
01/07/2017

Oriented Response Networks

Deep Convolution Neural Networks (DCNNs) are capable of learning unprece...

Please sign up or login with your details

Forgot password? Click here to reset