Learning Structured Inference Neural Networks with Label Relations

  • Hu H
  • Zhou G
  • Deng Z
 et al. 
  • 154


    Mendeley users who have this article in their library.
  • 8


    Citations of this article.


Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with fine-grained labels that describe major components, coarse-grained labels that depict high level abstraction or a set of labels that reveal attributes. Such categorization at different concept layers can be modeled with label graphs encoding label information. In this paper, we exploit this rich information with a state-of-art deep learning framework, and propose a generic structured model that leverages diverse label relations to improve image classification performance. Our approach employs a novel stacked label prediction neural network, capturing both inter-level and intra-level label semantics. We evaluate our method on benchmark image datasets, and empirical results illustrate the efficacy of our model.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Hexiang Hu

  • Guang-Tong Zhou

  • Zhiwei Deng

  • Zicheng Liao

  • Greg Mori

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free