Best Practices for Convolutional Neural Networks Applied to Object Recognition in Images

10/29/2019
by   Anderson de Andrade, et al.
0

This research project studies the impact of convolutional neural networks (CNN) in image classification tasks. We explore different architectures and training configurations with the use of ReLUs, Nesterov's accelerated gradient, dropout and maxout networks. We work with the CIFAR-10 dataset as part of a Kaggle competition to identify objects in images. Initial results show that CNNs outperform our baseline by acting as invariant feature detectors. Comparisons between different preprocessing procedures show better results for global contrast normalization and ZCA whitening. ReLUs are much faster than tanh units and outperform sigmoids. We provide extensive details about our training hyperparameters, providing intuition for their selection that could help enhance learning in similar situations. We design 4 models of convolutional neural networks that explore characteristics such as depth, number of feature maps, size and overlap of kernels, pooling regions, and different subsampling techniques. Results favor models of moderate depth that use an extensive number of parameters in both convolutional and dense layers. Maxout networks are able to outperform rectifiers on some models but introduce too much noise as the complexity of the fully-connected layers increases. The final discussion explains our results and provides additional techniques that could improve performance.

READ FULL TEXT
research
10/03/2017

A concatenating framework of shortcut convolutional neural networks

It is well accepted that convolutional neural networks play an important...
research
08/02/2022

Connection Reduction Is All You Need

Convolutional Neural Networks (CNN) increase depth by stacking convoluti...
research
02/04/2021

A Deeper Look into Convolutions via Pruning

Convolutional neural networks (CNNs) are able to attain better visual re...
research
02/20/2023

Kernel function impact on convolutional neural networks

This paper investigates the usage of kernel functions at the different l...
research
09/08/2017

Best Practices in Convolutional Networks for Forward-Looking Sonar Image Recognition

Convolutional Neural Networks (CNN) have revolutionized perception for c...
research
04/21/2016

TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks

In this paper we present a deep neural network topology that incorporate...
research
09/25/2019

Gated Channel Transformation for Visual Recognition

In this work, we propose a generally applicable transformation unit for ...

Please sign up or login with your details

Forgot password? Click here to reset