Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (5): 1383-1390.DOI: 10.11772/j.issn.1001-9081.2021071240

• Artificial intelligence • Previous Articles     Next Articles

Multi-label image classification method based on global and local label relationship

Wei REN(), Hexiang BAI   

  1. School of Computer and Information Technology,Shanxi University,Taiyuan Shanxi 030006,China
  • Received:2021-07-16 Revised:2021-08-31 Accepted:2021-09-14 Online:2021-09-28 Published:2022-05-10
  • Contact: Wei REN
  • About author:REN Wei, born in 1996, M. S. candidate. His research interests include deep learning, computer vision.
    BAI Hexiang, born in 1980, Ph. D., associate professor. His research interests include machine learning, data mining.
  • Supported by:
    National Natural Science Foundation of China(41871286)


任炜(), 白鹤翔   

  1. 山西大学 计算机与信息技术学院,太原 030006
  • 通讯作者: 任炜
  • 作者简介:任炜(1996—),男,山西襄汾人,硕士研究生,主要研究方向:深度学习、计算机视觉
  • 基金资助:


Considering the difficulty of modeling the interaction between labels and solidification of global label relationship in multi-label image classification tasks, a new Multiple-Label image classification method based on Global and Local Label Relationship (ML-GLLR) was proposed by combining self-attention mechanism and Knowledge Distillation (KD) method. Firstly, Convolutional Neural Network (CNN), semantic module and Dual Layer Self-Attention (DLSA) module were used by the Local Label Relationship (LLR) model to model local label relationship. Then, the KD method was used to make LLR learn global label relationship. The experimental results on the public datasets of MicroSoft Common Objects in COntext (MSCOCO) 2014 and PASCAL VOC challenge 2007 (VOC2007) show that, LLR improves the mean Average Precision (mAP) by 0.8 percentage points and 0.6 percentage points compared with Multiple Label classification based on Graph Convolutional Network (ML-GCN) respectively, and the proposed ML-GLLR increases the mAP by 0.2 percentage points and 1.3 percentage points compared with LLR. Experimental results show that, the proposed ML-GLLR can not only model the interaction between labels, but also avoid the problem of global label relationship solidification.

Key words: image classification, self-attention mechanism, deep learning, knowledge distillation, multi-label classification



关键词: 图像分类, 自注意力机制, 深度学习, 知识蒸馏, 多标签分类

CLC Number: