2019/08/10 by Dohyun Kim, Kyeorye Lee, Kim, Dohyun +8
Computer Science · Mathematics · #Anomaly Detection Techniques and Applications #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Data mining #FOS: Computer and information sciences #Harmony (color) #Harmony search #Imbalanced Data Classification Techniques #Machine Learning and Data Classification #Machine learning #Mathematics #Network model #Pattern recognition (psychology) #Standard deviation #Statistics #cs.CV
paper · pdf · doi:10.48550/arxiv.1908.03671
published in arXiv (Cornell University) (Cornell University)
arxiv created 2019/08/10 · openalex publication_date 2019/08/10 · arxiv updated 2019/08/13 · openalex created_date 2019/08/22 · openalex updated_date 2026/07/28
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.