The Case for High-Accuracy Classification: Think Small, Think Many!

TL;DR

This paper introduces a lightweight ensemble of simple models using color features for high-accuracy image classification, achieving better accuracy and faster inference than deep models like ResNet-50, especially for resource-limited devices.

Contribution

The paper proposes a novel ensemble approach based on simple color features, demonstrating significant accuracy improvements and faster inference for classification tasks.

Findings

Higher prediction accuracy than ResNet-50

7.64x faster inference

Lower computational cost

Abstract

To facilitate implementation of high-accuracy deep neural networks especially on resource-constrained devices, maintaining low computation requirements is crucial. Using very deep models for classification purposes not only decreases the neural network training speed and increases the inference time, but also need more data for higher prediction accuracy and to mitigate false positives. In this paper, we propose an efficient and lightweight deep classification ensemble structure based on a combination of simple color features, which is particularly designed for "high-accuracy" image classifications with low false positives. We designed, implemented, and evaluated our approach for explosion detection use-case applied to images and videos. Our evaluation results based on a large test test show considerable improvements on the prediction accuracy compared to the popular ResNet-50 model, while benefiting from 7.64x faster inference and lower computation cost. While we applied our approach to explosion detection, our approach is general and can be applied to other similar classification use cases as well. Given the insight gained from our experiments, we hence propose a "think small, think many" philosophy in classification scenarios: that transforming a single, large, monolithic deep model into a verification-based step model ensemble of multiple small, simple, lightweight models with narrowed-down color spaces can possibly lead to predictions with higher accuracy.