Fusing CNNs and statistical indicators to improve image classification

TL;DR

This paper presents an ensemble approach combining CNN features with statistical indicators to enhance image classification accuracy cost-effectively, outperforming larger CNNs on multiple datasets.

Contribution

It introduces a novel ensemble method that fuses CNN-derived features with statistical indicators, improving classification performance without increasing network size.

Findings

Improved accuracy in 8 of 9 datasets

Over 10% precision increase in two datasets

Cost-effective alternative to larger CNNs

Abstract

Convolutional Networks have dominated the field of computer vision for the last ten years, exhibiting extremely powerful feature extraction capabilities and outstanding classification performance. The main strategy to prolong this trend relies on further upscaling networks in size. However, costs increase rapidly while performance improvements may be marginal. We hypothesise that adding heterogeneous sources of information may be more cost-effective to a CNN than building a bigger network. In this paper, an ensemble method is proposed for accurate image classification, fusing automatically detected features through Convolutional Neural Network architectures with a set of manually defined statistical indicators. Through a combination of the predictions of a CNN and a secondary classifier trained on statistical features, better classification performance can be cheaply achieved. We test multiple learning algorithms and CNN architectures on a diverse number of datasets to validate our proposal, making public all our code and data via GitHub. According to our results, the inclusion of additional indicators and an ensemble classification approach helps to increase the performance in 8 of 9 datasets, with a remarkable increase of more than 10% precision in two of them.