본문 바로가기
  • Home

An Efficient Deep Learning Ensemble Using a Distribution of Label Embedding

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2021, 26(1), pp.27-35
  • DOI : 10.9708/jksci.2021.26.01.027
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : November 4, 2020
  • Accepted : January 4, 2021
  • Published : January 29, 2021

PARK SAEROM 1

1성신여자대학교

Accredited

ABSTRACT

In this paper, we propose a new stacking ensemble framework for deep learning models which reflects the distribution of label embeddings. Our ensemble framework consists of two phases: training the baseline deep learning classifier, and training the sub-classifiers based on the clustering results of label embeddings. Our framework aims to divide a multi-class classification problem into small sub-problems based on the clustering results. The clustering is conducted on the label embeddings obtained from the weight of the last layer of the baseline classifier. After clustering, sub-classifiers are constructed to classify the sub-classes in each cluster. From the experimental results, we found that the label embeddings well reflect the relationships between classification labels, and our ensemble framework can improve the classification performance on a CIFAR 100 dataset.

Citation status

* References for papers published after 2022 are currently being built.

This paper was written with support from the National Research Foundation of Korea.