# Deep ensemble network with explicit complementary model for accuracy-balanced classification

## TL;DR

This paper introduces Harmony, a deep ensemble network with three sub-models designed to improve classification accuracy and reduce accuracy deviation among categories without sacrificing overall accuracy.

## Contribution

The paper proposes a novel ensemble framework with explicit complementary models and a conductor to balance accuracy across categories, addressing accuracy deviation issues.

## Key findings

- Harmony reduces accuracy deviation among categories.
- Harmony maintains high overall classification accuracy.
- Experimental results validate the effectiveness of Harmony.

## Abstract

The average accuracy is one of major evaluation metrics for classification systems, while the accuracy deviation is another important performance metric used to evaluate various deep neural networks. In this paper, we present a new ensemble-like fast deep neural network, Harmony, that can reduce the accuracy deviation among categories without degrading overall average accuracy. Harmony consists of three sub-models, namely, Target model, Complementary model, and Conductor model. In Harmony, an object is classified by using either Target model or Complementary model. Target model is a conventional classification network for general categories, while Complementary model is a classification network especially for weak categories that are inaccurately classified by Target model. Conductor model is used to select one of two models. Experimental results demonstrate that Harmony accurately classifies categories, while it reduces the accuracy deviation among the categories.